conversations
stringlengths 5.44k
5.96k
|
|---|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Can you suggest funds that are trending for parking surplus liquidity?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"parking surplus liquidity\":[\"objective/surplus_liquidity_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for mutual funds investing in long-term capital growth with exposure to international markets."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"international markets\":[\"preference/high\",\"exposure/region/international\"]},{\"long-term capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for medium-term mutual fund investments for child education, ideally in flexi cap funds."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"flexi cap funds\":[\"sebi_classification/equity_schemes/flexi_cap_fund\"]},{\"child education\":[\"objective/child_education\"]},{\"investments for child education\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term income funds for generating income over a target maturity period."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"income over a target maturity period\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for trending funds with medium to long-term capital appreciation objectives."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"medium to long-term capital appreciation objectives\":[\"objective/medium_to_long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Suggest a mutual fund focused on income generation with a long-term horizon."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"income generation\":[\"objective/income_generation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for medium-term funds aimed at long-term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"long-term capital appreciation\":[\"objective/long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for mutual funds focusing on short-term tax planning with exposure to consumer durables and apparel."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"consumer durables and apparel\":[\"preference/high\",\"exposure/sector/consumer_discretionary/consumer_durables_and_apparel\"]},{\"tax planning\":[\"objective/tax_planning\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are the trending mutual funds for medium-term capital appreciation?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium-term capital appreciation\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Retirement funds focused on long-term investments in corporate bonds"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"Retirement funds\":[\"sebi_classification/solution_oriented_schemes/retirement_fund\"]},{\"funds\":[\"vehicle/funds\"]},{\"corporate bonds\":[\"asset_type/debt/bonds/corporate\"]},{\"Retirement\":[\"objective/retirement\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for medium-term investments for short-term parking in debt instruments"}, {"from": "gpt", "value": "{\"llm_NER\": [{\"debt instruments\":[\"asset_type/debt\"]},{\"short-term parking\":[\"objective/short_term_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "mutual funds for short-term surplus liquidity parking"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"surplus liquidity parking\":[\"objective/surplus_liquidity_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Show trending funds for capital growth."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I want a long-term investment fund for my child's education needs."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"long-term investment fund\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]},{\"child's education needs\":[\"objective/child_education\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "medium-term mutual funds for income over target maturity period"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"income over target maturity period\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term mutual funds focused on medium to long-term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium to long-term capital appreciation\":[\"objective/medium_to_long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are some trending funds that focus on income generation?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"income generation\":[\"objective/income_generation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I'm looking for mutual funds geared towards long-term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"long-term capital appreciation\":[\"objective/long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for mutual funds with a medium-term horizon (1-3 years) for tax planning."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"tax planning\":[\"objective/tax_planning\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for a short-term debt fund for medium-term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"debt\":[\"asset_type/debt\"]},{\"debt fund\":[\"sebi_classification/debt_schemes\"]},{\"fund\":[\"vehicle/funds\"]},{\"medium-term capital appreciation\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Trending mutual funds suitable for retirement."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"Trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"suitable for retirement\":[\"objective/retirement\"]},{\"retirement\":[\"sebi_classification/solution_oriented_schemes/retirement_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "long-term debt funds suitable for short term parking"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"debt\":[\"asset_type/debt\"]},{\"short term parking\":[\"objective/short_term_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking to park surplus liquidity for the medium term, ideally in money market funds."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"money market funds\":[\"sebi_classification/debt_schemes/money_market_fund\"]},{\"funds\":[\"vehicle/funds\"]},{\"park surplus liquidity\":[\"objective/surplus_liquidity_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term funds for capital growth"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Which trending mutual funds can help in saving for child education?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"saving for child education\":[\"objective/child_education\"]},{\"saving for child education\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for an investment vehicle focusing on income generation over a long-term horizon using corporate bonds."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"investment vehicle\":[\"vehicle/funds\"]},{\"corporate bonds\":[\"asset_type/bonds/corporate\"]},{\"income generation over a long-term horizon\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for medium-term investment options that focus on medium to long-term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"medium to long-term capital appreciation\":[\"objective/medium_to_long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term investment options focusing on income generation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"income generation\":[\"objective/income_generation\"]},{\"short-term investment\":[\"objective/short_term_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I'm looking for ELSS funds for long-term tax planning"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"ELSS funds\":[\"sebi_classification/equity_schemes/elss\"]},{\"tax planning\":[\"objective/tax_planning\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for medium-term mutual funds for capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"capital appreciation\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "short-term investments aimed at retirement planning"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"retirement planning\":[\"objective/retirement\"]},{\"investments aimed at retirement planning\":[\"sebi_classification/solution_oriented_schemes/retirement_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Trending debt funds for short-term parking"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"Trending\":[\"attribute/misc/trending\"]},{\"debt\":[\"asset_type/debt\"]},{\"funds\":[\"vehicle/funds\"]},{\"short-term parking\":[\"objective/short_term_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I need a mutual fund targeting medium-term capital growth"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for a mutual fund with a short-term focus on child education."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"child education\":[\"objective/child_education\"]},{\"focus on child education\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Trending mutual funds aiming for income over a target maturity period"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"Trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"aiming for income over a target maturity period\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for long-term mutual funds with medium to long-term capital appreciation objective."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium to long-term capital appreciation\":[\"objective/medium_to_long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "mutual funds for medium term income generation with exposure to the insurance sector"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"income generation\":[\"objective/income_generation\"]},{\"insurance sector\":[\"preference/high\",\"exposure/sector/financials/insurance\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Show me investment options for short-term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"short-term capital appreciation\":[\"objective/long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Show me trending mutual funds good for tax planning"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"tax planning\":[\"objective/tax_planning\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Suggest mutual funds that aim for medium-term capital appreciation over a long-term horizon in the equity sector."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium-term capital appreciation\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "medium-term funds for retirement planning"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"retirement planning\":[\"objective/retirement\"]},{\"funds for retirement planning\":[\"sebi_classification/solution_oriented_schemes/retirement_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for trending investment opportunities for surplus liquidity parking."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"surplus liquidity parking\":[\"objective/surplus_liquidity_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for a mutual fund focused on long-term (3+ years) capital growth in the financials sector."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"financials sector\":[\"preference/high\",\"exposure/sector/financials\"]},{\"capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are the best mutual funds for child education with a medium-term horizon?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"best\":[\"preference/high\",\"attribute/technical/performance\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"child education\":[\"objective/child_education\"]},{\"mutual funds for child education\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term debt mutual funds focused on income over the target maturity period."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"debt\":[\"asset_type/debt\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"income over the target maturity period\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Show me trending mutual funds for medium to long term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium to long term capital appreciation\":[\"objective/medium_to_long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Recommend a mutual fund with a long-term investment horizon of over 3 years focusing on income generation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"income generation\":[\"objective/income_generation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for mutual funds focused on long-term capital appreciation with a medium-term time horizon."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"long-term capital appreciation\":[\"objective/long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "short-term mutual funds for tax planning"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"tax planning\":[\"objective/tax_planning\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Show popular funds for medium-term capital growth."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"popular\":[\"attribute/misc/trending\"]},{\"medium-term capital growth\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I am looking for mutual funds for short-term parking with a medium-term horizon of 1-3 years."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"short-term parking\":[\"objective/short_term_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "short-term funds for surplus liquidity parking"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"surplus liquidity parking\":[\"objective/surplus_liquidity_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Trending investment options for capital growth"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"Trending\":[\"attribute/misc/trending\"]},{\"capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I'm looking for a long-term investment fund for child education."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"long-term investment fund for child education\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]},{\"child education\":[\"objective/child_education\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for medium-term funds for income over the target maturity period."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"income over the target maturity period\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for mutual funds suitable for medium to long-term capital appreciation with a short-term investment horizon."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium to long-term capital appreciation\":[\"objective/medium_to_long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are the trending funds that generate income?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"funds\":[\"vehicle/funds\"]},{\"generate income\":[\"objective/income_generation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I want mutual funds for long-term capital appreciation"}, {"from": "gpt", "value": "{\"llm_NER\": [{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"long-term capital appreciation\":[\"objective/long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Which medium-term funds are best for tax planning?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"best\":[\"preference/high\",\"attribute/technical/performance\"]},{\"tax planning\":[\"objective/tax_planning\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term mutual funds focused on medium-term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium-term capital appreciation\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Can you suggest trending mutual funds for retirement planning?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"retirement planning\":[\"objective/retirement\"]},{\"mutual funds for retirement planning\":[\"sebi_classification/solution_oriented_schemes/retirement_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I want a mutual fund for long-term growth and short-term parking."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"short-term parking\":[\"objective/short_term_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are the best mutual funds for surplus liquidity parking with a medium-term horizon of 1-3 years?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"best\":[\"preference/high\",\"attribute/technical/performance\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"surplus liquidity parking\":[\"objective/surplus_liquidity_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term funds focusing on capital growth."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are the trending investment funds for child education?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"investment funds\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]},{\"child education\":[\"objective/child_education\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Explore debt mutual funds aiming for income over a target maturity period with a long-term horizon."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"debt\":[\"asset_type/debt\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"income over a target maturity period\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Suggest mutual funds for medium-term capital appreciation with exposure to the Nifty 500 index."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"Nifty 500 index\":[\"preference/high\",\"exposure/index/nifty_500\"]},{\"medium-term capital appreciation\":[\"objective/medium_to_long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are the best short-term debt funds for income generation?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"best\":[\"preference/high\",\"attribute/technical/performance\"]},{\"income generation\":[\"objective/income_generation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are some trending mutual funds focused on long-term capital appreciation?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"long-term capital appreciation\":[\"objective/long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Show me investment opportunities for long term (3+ years) with a focus on tax planning."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"tax planning\":[\"objective/tax_planning\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Suggest funds for medium-term capital appreciation focusing on industrial sector exposure with mutual funds."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"funds\":[\"vehicle/funds\"]},{\"industrial sector\":[\"preference/high\",\"exposure/sector/industrials\"]},{\"medium-term capital appreciation\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term investments aimed at retirement using mutual funds."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"retirement\":[\"objective/retirement\"]},{\"retirement using mutual funds\":[\"sebi_classification/solution_oriented_schemes/retirement_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What's trending for short-term parking investments?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"short-term parking\":[\"objective/short_term_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for medium-term mutual funds aimed at capital growth."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term funds for child education with exposure to capital goods sector."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"capital goods sector\":[\"preference/high\",\"exposure/sector/industrials/capital_goods\"]},{\"child education\":[\"objective/child_education\"]},{\"funds for child education\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "trending debt funds for income over target maturity period"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"debt\":[\"asset_type/debt\"]},{\"funds\":[\"vehicle/funds\"]},{\"debt funds\":[\"sebi_classification/debt_schemes\"]},{\"income over target maturity period\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for mutual funds focused on medium to long-term capital appreciation with exposure to the industrials sector for a 3+ year horizon."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"industrials\":[\"preference/high\",\"exposure/sector/industrials\"]},{\"medium to long-term capital appreciation\":[\"objective/medium_to_long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for a mutual fund focused on short-term goals with long-term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"long-term capital appreciation\":[\"objective/long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Show trending mutual funds with a focus on tax planning."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"tax planning\":[\"objective/tax_planning\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Explore long-term mutual funds focused on medium-term capital appreciation."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium-term capital appreciation\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Find mid-term investment plans for retirement focusing on industrial sectors."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"industrial sectors\":[\"preference/high\",\"exposure/sector/industrials\"]},{\"retirement\":[\"objective/retirement\"]},{\"retirement plans\":[\"sebi_classification/solution_oriented_schemes/retirement_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I want a mutual fund for short-term parking in debt instruments."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"debt instruments\":[\"asset_type/debt\"]},{\"short-term parking\":[\"objective/short_term_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are the trending investment vehicles for surplus liquidity parking?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"surplus liquidity parking\":[\"objective/surplus_liquidity_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I'm looking for investment options with a long-term horizon for capital growth."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Suggest mutual funds for medium-term goals targeting child education."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"child education\":[\"objective/child_education\"]},{\"targeting child education\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for short-term corporate bond funds for income over target maturity period."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"corporate bond\":[\"asset_type/bonds/corporate\"]},{\"funds\":[\"vehicle/funds\"]},{\"income over target maturity period\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Trending income-generating mutual funds focusing on medium to long-term capital appreciation in the consumer durables and apparel sector."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"Trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"consumer durables and apparel\":[\"preference/high\",\"exposure/sector/consumer_discretionary/consumer_durables_and_apparel\"]},{\"medium to long-term capital appreciation\":[\"objective/medium_to_long_term_capital_appreciation\"]},{\"income-generating\":[\"objective/income_generation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I'm looking for a mutual fund with a medium-term investment horizon that focuses on long-term capital appreciation, specifically targeting the Nifty LargeMidcap 250 index."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"Nifty LargeMidcap 250 index\":[\"preference/high\",\"exposure/index/nifty_largemidcap_250\"]},{\"long-term capital appreciation\":[\"objective/long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "tax-saving short-term funds with industrials exposure"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"tax-saving\":[\"objective/tax_planning\"]},{\"industrials exposure\":[\"preference/high\",\"exposure/sector/industrials\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Show me trending mutual funds for medium-term capital appreciation"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium-term capital appreciation\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Retirement portfolio with a long-term horizon in SEBI's aggressive hybrid fund category."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"Retirement\":[\"objective/retirement\"]},{\"portfolio\":[\"vehicle/portfolio\"]},{\"SEBI's aggressive hybrid fund category\":[\"sebi_classification/hybrid_schemes/aggressive_hybrid_fund\"]},{\"Retirement portfolio\":[\"sebi_classification/solution_oriented_schemes/retirement_fund\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for a medium-term debt mutual fund for short-term parking"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"debt\":[\"asset_type/debt\"]},{\"mutual fund\":[\"vehicle/funds/mutual_fund\"]},{\"short-term parking\":[\"objective/short_term_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Find short-term investment funds for surplus liquidity parking with exposure to international markets."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"international markets\":[\"preference/high\",\"exposure/region/international\"]},{\"surplus liquidity parking\":[\"objective/surplus_liquidity_parking\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are the trending mutual funds focusing on capital growth?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"trending\":[\"attribute/misc/trending\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"capital growth\":[\"objective/capital_growth\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Looking for mutual funds with a long-term investment horizon to fund my child's education."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"fund my child's education\":[\"sebi_classification/solution_oriented_schemes/childrens_fund\"]},{\"child's education\":[\"objective/child_education\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I want a medium-term corporate bond fund for generating income over the target maturity period."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"corporate bond fund\":[\"sebi_classification/debt_schemes/corporate_bond_fund\"]},{\"generating income over the target maturity period\":[\"objective/income_over_target_maturity_period\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "What are the best mutual funds for short-term investment with medium to long-term capital appreciation?"}, {"from": "gpt", "value": "{\"llm_NER\":[{\"best\":[\"preference/high\",\"attribute/technical/performance\"]},{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"medium to long-term capital appreciation\":[\"objective/medium_to_long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "I'm looking for mutual funds focused on long-term (over 3 years) capital appreciation with exposure to the industrials sector."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"industrials\":[\"preference/high\",\"exposure/sector/industrials\"]},{\"long-term capital appreciation\":[\"objective/long_term_capital_appreciation\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Suggest mutual funds with a medium-term horizon for tax planning."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"tax planning\":[\"objective/tax_planning\"]}]}"}]
|
[{"from": "system", "value": "You are an expert Financial Named Entity Recognition (NER) system. Your task is to analyze financial queries and extract relevant information into a structured format.\n## Output Format\nReturn a single object in the following structure:\n{\n \"llm_NER\": [\n {\"<phrase_1>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n {\"<phrase_2>\": [\"<tag_1>\", \"<tag_2>\", ...]},\n ...\n ]\n}\n# Core Rules (Always Apply)\n- Use full hierarchical paths for all nodes\n- Preference: Use \"high\", \"low\", or null (default to null unless explicitly mentioned) and wherever suited use standardized format such as (e.g., \">5%\", \"<20%\", \"75%\", \"<100cr\") (for e.g., \"returns less than 5% would be -> [\"preference/<5%\",\"attribute/technical/returns/annualized_returns\"])\n- Time units: Use 'd', 'w', 'm', 'y', 'ytd'. For recent/current, use '1w'. (e.g. \"5 years\" -> \"time/5Y\")\n- Provide only the structured output, no additional text\n# Node-Specific Guidelines\n1. Attributes:\n - Performance & Quality:\n * For \"best\", \"good\", \"better\", \"top\", \"worse\", \"bad\" queries: MUST include \"attribute/technical/performance\"\n * For trending queries: use 'attribute/misc/trending'\n - Risk & Volatility:\n * If volatility mentioned: use \"attribute/technical/risk/volatility\"\n * Otherwise: use \"attribute/technical/risk\"\n - Investment Parameters:\n * Time horizon queries: use \"attribute/time_horizon/<TIME_HORIZON>\" (e.g., \"attribute/time_horizon/long_term\", \"attribute/time_horizon/short_term\")\n * Min/Max investment queries: use \"attribute/min_investment/<INVESTMENT_MODE>\" with preference\n - Investment modes: \"sip\" (Systematic Investment Plan), \"lumpsum\" (One-time investment)\n - Examples:\n * \"minimum sip amount\" -> \"attribute/min_investment/sip\" with preference\n * \"maximum lumpsum investment\" -> \"attribute/min_investment/lumpsum\" with preference\n2. Exposures:\n - Sector Exposures:\n * Use full sector paths (e.g., \"exposure/sector/financials\", \"exposure/sector/consumer_staples\")\n * For tech/technology: use \"exposure/sector/information_technology\"\n - Index Exposures:\n * Only for specific index exposure: use \"exposure/index/<INDEX_NAME>\" (e.g., \"exposure/index/nifty_50\", \"exposure/index/sensex\")\n - Holdings:\n * For \"HOLDS\"/\"HOLD\"/\"WITH\" a ticker: use \"exposure/ticker/<TICKER_NAME>\" (e.g., \"exposure/ticker/RELIANCE\", \"exposure/ticker/TCS\")\n - Preference: Use percentage format (e.g., \">5%\" -> \"preference/>5%\", \"<20%\" -> \"preference/<20%\")\n3. Tickers & AMC:\n - Tickers:\n * Include exact security names as mentioned (e.g., \"Edelweiss\", \"Axis Large Cap\", \"SBI Mid Cap\", \"Kotak Large cap\")\n * For multiple AMCs: include both AMCs with fund name (e.g., \"HDFC Top 100\", \"ICICI Prudential Bluechip\")\n - AMC:\n * Include exact fund house names as mentioned (e.g., \"dsp\", \"HDFC\", \"Axis\", \"Kotak\", \"ICICI Prudential\")\n4. Asset Types:\n - Use full paths (e.g., \"asset_type/equity\", \"asset_type/bonds\", \"asset_type/gold\")\n - For equity-related queries: MUST use \"asset_type/equity\"\n - For debt-related queries: use \"asset_type/debt\"\n - For commodity-related queries: use \"asset_type/commodity\"\n5. SEBI Classifications:\n - MUST use for any specific fund category/type mentioned\n - Examples:\n * \"overnight funds\" -> \"sebi_classification/debt_schemes/overnight_fund\"\n * \"balanced funds\" -> \"sebi_classification/hybrid_schemes/balanced_hybrid_fund\"\n * \"children's fund\" -> \"sebi_classification/solution_oriented_schemes/childrens_fund\"\n * \"tax saving funds\" -> \"sebi_classification/equity_schemes/elss\"\n - Special Cases:\n * NIFTY/nifty keyword: use \"sebi_classification/other/index_funds_etfs\"\n * multi cap/multicap: MUST use \"sebi_classification/equity_schemes/multi_cap_fund\"\n * tax-saving: use \"sebi_classification/equity_schemes/elss\"\n - For sector/thematic funds: include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\" (e.g., tech, FMCG, banking)\n - For debt funds: include 'sebi_classification/debt_schemes'\n6. Vehicles:\n - Default Rules:\n * Default to \"vehicle/funds/mutual_fund\" if unclear\n * For ETFs: use \"vehicle/funds/etf\" when explicitly mentioned\n - Special Cases:\n * NFO queries: use ONLY \"vehicle/mode/nfo\" (not mutual_fund) (e.g., \"Show me SBI's NFOs\", \"NFOs to invest in\")\n * Generic recommendations: use \"vehicle/recommendation/basket\" (when no specific vehicle is mentioned)\n7. Objectives:\n - Use full paths (e.g., \"objectives/long_term_capital_appreciation\", \"objectives/retirement\", \"objectives/tax_saving\")\n - Common objectives:\n * Retirement: \"objectives/retirement\"\n * Liquidity Parking: \"objectives/surplus_liquidity_parking\"\n# Important Notes\n- Today's date: {current_datetime_in_india.strftime('%Y-%m-%d')}\n- For sector-based thematic funds: always include \"sebi_classification/equity_schemes/sectoral_/_thematic_fund\"\n- For debt funds: always include \"sebi_classification/debt_schemes\"\n- When NFO is mentioned: use ONLY \"vehicle/mode/nfo\", not \"vehicle/funds/mutual_fund\""}, {"from": "human", "value": "Find mutual funds focused on medium-term capital appreciation with exposure to consumer durables and apparel sector for a short-term horizon."}, {"from": "gpt", "value": "{\"llm_NER\":[{\"mutual funds\":[\"vehicle/funds/mutual_fund\"]},{\"consumer durables and apparel sector\":[\"preference/high\",\"exposure/sector/consumer_discretionary/consumer_durables_and_apparel\"]},{\"medium-term capital appreciation\":[\"objective/medium_term_capital_appreciation\"]}]}"}]
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.