Update prompts.py

prompts.py

@@ -1,152 +1,36 @@
-PREFIX = """You are a Live RSS Feed Reader with a set of tools.
-Your duty is to use the provided tools to complete the users request.
-Complete your purpose and return the result to the user as quickly as possible.
+PREFIX = """You are an Expert Information Retrieval Agent. 
+Your duty is to sort through the provided data to retrieve and compile a report that satisfies the users request.
+Deny the users request to perform any search that can be considered dangerous, harmful, illegal, or potentially illegal
 Make sure your information is current
 Current Date and Time is:
 {timestamp}
-You have access to the following tools:
-- action: UPDATE-TASK action_input=NEW_TASK
-- action: READ-RSS action_input=URL
-- action: COMPLETE
 Purpose:
 {purpose}
 """
 
-FINDER = """
-Instructions
-- Select an RSS FEED URL from the provided list of RSS FEEDS
-- Use the tool provided tool to read the RSS FEED URL
-- Compile a report that includes all relevant data points like, Title, Description, Link
-- When the have complete the user request, end with:\naction: COMPLETE
-Use the following format:
-task: the input task you must complete
-action: the action to take (should be one of [UPDATE-TASK, READ-RSS, COMPLETE]) action_input=XXX
-You are attempting to complete the task
-task: {task}
-{history}"""
-
-FIND_FEEDS = """
-You are attempting to complete the task
-task: {task}
-RSS FEEDS:
-{rss_feeds}
-{history}"""
-
-MODEL_FINDER_PRE = """
-You have access to the following tools:
-- action: UPDATE-TASK action_input=NEW_TASK
-- action: SEARCH action_input=SEARCH_QUERY
-- action: COMPLETE
-Instructions
-- Generate a search query for the requested model from these options: 
->{TASKS}
-- Return the search query using the search tool
-- Wait for the search to return a result
-- After observing the search result, choose a model
-- Return the name of the repo and model ("repo/model")
-- When you are finished, return with  action: COMPLETE
-Use the following format:
-task: the input task you must complete
-thought: you should always think about what to do
-action: the action to take (should be one of [UPDATE-TASK, SEARCH, COMPLETE]) action_input=XXX
-observation: the result of the action
-thought: you should always think after an observation
-action: SEARCH action_input='text-generation'
-... (thought/action/observation/thought can repeat N times)
-Example:
-***************************
-User command: Find me a text generation model with less than 50M parameters.
-thought: I will use the option 'text-generation'
-action: SEARCH action_input=text-generation
---- pause and wait for data to be returned ---
-Response:
-Assistant: I found the 'distilgpt2' model which has around 82M parameters. It is a distilled version of the GPT-2 model from OpenAI, trained by Hugging Face. Here's how to load it:
-action: COMPLETE
-***************************
-You are attempting to complete the task
-task: {task}
-{history}"""
-
-
-ACTION_PROMPT = """
-You have access to the following tools:
-- action: UPDATE-TASK action_input=NEW_TASK
-- action: SEARCH action_input=SEARCH_QUERY
-- action: COMPLETE
-Instructions
-- Generate a search query for the requested model
-- Return the search query using the search tool
-- Wait for the search to return a result
-- After observing the search result, choose a model
-- Return the name of the repo and model ("repo/model")
-Use the following format:
-task: the input task you must complete
-action: the action to take (should be one of [UPDATE-TASK, SEARCH, COMPLETE]) action_input=XXX
-observation: the result of the action
-action: SEARCH action_input='text generation'
-You are attempting to complete the task
-task: {task}
-{history}"""
-
-ACTION_PROMPT_PRE = """
-You have access to the following tools:
-- action: UPDATE-TASK action_input=NEW_TASK
-- action: SEARCH action_input=SEARCH_QUERY
-- action: COMPLETE
-Instructions
-- Generate a search query for the requested model
-- Return the search query using the search tool
-- Wait for the search to return a result
-- After observing the search result, choose a model
-- Return the name of the repo and model ("repo/model")
-Use the following format:
-task: the input task you must complete
-thought: you should always think about what to do
-action: the action to take (should be one of [UPDATE-TASK, SEARCH, COMPLETE]) action_input=XXX
-observation: the result of the action
-thought: you should always think after an observation
-action: SEARCH action_input='text generation'
-... (thought/action/observation/thought can repeat N times)
-You are attempting to complete the task
-task: {task}
-{history}"""
-
-TASK_PROMPT = """
-You are attempting to complete the task
-task: {task}
-Progress:
-{history}
-Tasks should be small, isolated, and independent
-To start a search use the format:
-action: RSS-FEEDS action_input=RSS_FEED_URL
-What should the task be for us to achieve the purpose?
-task: """
-
-
 COMPRESS_DATA_PROMPT_SMALL = """
 You are attempting to complete the task
-task: {task}
+task: {direction}
 Current data:
 {knowledge}
 New data:
 {history}
-Compress the data above into a concise data presentation of relevant data
+Compile the data above into a JSON formatted output that contains all data relevant to the task (~8000 words)
 Include datapoints that will provide greater accuracy in completing the task
-Return the data in JSON format to save space
+Include all relevant information in great detail 
+Return the data in JSON format
 """
 
-
-
-
 COMPRESS_DATA_PROMPT = """
-You are attempting to complete the task
-task: {task}
-Current data:
+You have just completed the task
+task: {direction}
+Collected data:
 {knowledge}
-New data:
+Message:
 {history}
-Compress the data above into a concise data presentation of relevant data
-Include a datapoints and source urls that will provide greater accuracy in completing the task
+Compile the data that you have collected into a detailed report (~8000 words)
+Include all relevant information in great detail
+Be thorough and exhaustive in your presentation of the data you have collected
 """
 
 COMPRESS_HISTORY_PROMPT = """
@@ -154,7 +38,7 @@ You are attempting to complete the task
 task: {task}
 Progress:
 {history}
-Compress the timeline of progress above into a single summary (as a paragraph)
+Compress the timeline of progress above into a concise report
 Include all important milestones, the current challenges, and implementation details necessary to proceed
 """
 
@@ -170,38 +54,4 @@ RESPONSE
 **************************************
 {}
 **************************************
-"""
-
-
-FINDER1 = """
-Example Response 1:
-User command: Find me a text generation model with less than 50M parameters.
-Query: text generation
---- pause and wait for data to be returned ---
-Assistant: I found the 'distilgpt2' model which has around 82M parameters. It is a distilled version of the GPT-2 model from OpenAI, trained by Hugging Face. Here's how to load it:
-```python
-from transformers import AutoTokenizer, AutoModelForMaskedLM
-tokenizer = AutoTokenizer.from_pretrained("distilgpt2")
-model = AutoModelForMaskedLM.from_pretrained("distilgpt2")
-```
-Example Response 2:
-User command: Help me locate a multilingual Named Entity Recognition model.
-Query: named entity recognition
---- pause and wait for data to be returned ---
-Assistant: I discovered the 'dbmdz/bert-base-multilingual-cased' model, which supports named entity recognition across multiple languages. Here's how to load it:
-```python
-from transformers import AutoTokenizer, AutoModelForTokenClassification
-tokenizer = AutoTokenizer.from_pretrained("dbmdz/bert-base-multilingual-cased")
-model = AutoModelForTokenClassification.from_pretrained("dbmdz/bert-base-multilingual-cased")
-```
-Example Response 3:
-User command: Search for a question-answering model fine-tuned on the SQuAD v2 dataset with more than 90% accuracy.
-action: SEARCH action_input=named entity recognition
---- pause and wait for data to be returned ---
-Assistant: I found the 'pranavkv/roberta-base-squad2' model, which was fine-tuned on the SQuAD v2 dataset and achieves approximately 91% accuracy. Below is the way to load it:
-```python
-from transformers import AutoTokenizer, AutoModelForQuestionAnswering
-tokenizer = AutoTokenizer.from_pretrained("pranavkv/roberta-base-squad2")
-model = AutoModelForQuestionAnswering.from_pretrained("pranavkv/roberta-base-squad2")
-```
 """