Prakhar Bhandari commited on
Commit
4546b0a
Β·
1 Parent(s): 4f70c47

Updated KG Creation

Browse files
Files changed (1) hide show
  1. kg_creation.ipynb +164 -83
kg_creation.ipynb CHANGED
@@ -2,7 +2,7 @@
2
  "cells": [
3
  {
4
  "cell_type": "code",
5
- "execution_count": 2,
6
  "metadata": {},
7
  "outputs": [],
8
  "source": [
@@ -27,7 +27,7 @@
27
  },
28
  {
29
  "cell_type": "code",
30
- "execution_count": 13,
31
  "metadata": {},
32
  "outputs": [
33
  {
@@ -37,12 +37,9 @@
37
  "Requirement already satisfied: langchain in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (0.1.16)\n",
38
  "Requirement already satisfied: neo4j in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (5.19.0)\n",
39
  "Requirement already satisfied: openai in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (1.23.2)\n",
40
- "Collecting wikipedia\n",
41
- " Downloading wikipedia-1.4.0.tar.gz (27 kB)\n",
42
- " Preparing metadata (setup.py) ... \u001b[?25ldone\n",
43
- "\u001b[?25hRequirement already satisfied: tiktoken in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (0.6.0)\n",
44
- "Collecting langchain_openai\n",
45
- " Downloading langchain_openai-0.1.3-py3-none-any.whl.metadata (2.5 kB)\n",
46
  "Requirement already satisfied: PyYAML>=5.3 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from langchain) (6.0.1)\n",
47
  "Requirement already satisfied: SQLAlchemy<3,>=1.4 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from langchain) (2.0.29)\n",
48
  "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from langchain) (3.9.5)\n",
@@ -87,15 +84,7 @@
87
  "Requirement already satisfied: urllib3<3,>=1.21.1 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from requests<3,>=2->langchain) (2.2.1)\n",
88
  "Requirement already satisfied: greenlet!=0.4.17 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from SQLAlchemy<3,>=1.4->langchain) (3.0.3)\n",
89
  "Requirement already satisfied: soupsieve>1.2 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from beautifulsoup4->wikipedia) (2.5)\n",
90
- "Requirement already satisfied: mypy-extensions>=0.3.0 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain) (1.0.0)\n",
91
- "Downloading langchain_openai-0.1.3-py3-none-any.whl (33 kB)\n",
92
- "Building wheels for collected packages: wikipedia\n",
93
- " Building wheel for wikipedia (setup.py) ... \u001b[?25ldone\n",
94
- "\u001b[?25h Created wheel for wikipedia: filename=wikipedia-1.4.0-py3-none-any.whl size=11678 sha256=8579328fd821efddb0b23c1aed4bccd2d0f77a18118ee2e2a9e69badd2d5aa0d\n",
95
- " Stored in directory: /local/home/pbhandari/.cache/pip/wheels/c2/46/f4/caa1bee71096d7b0cdca2f2a2af45cacf35c5760bee8f00948\n",
96
- "Successfully built wikipedia\n",
97
- "Installing collected packages: wikipedia, langchain_openai\n",
98
- "Successfully installed langchain_openai-0.1.3 wikipedia-1.4.0\n"
99
  ]
100
  }
101
  ],
@@ -105,7 +94,7 @@
105
  },
106
  {
107
  "cell_type": "code",
108
- "execution_count": 6,
109
  "metadata": {},
110
  "outputs": [],
111
  "source": [
@@ -123,7 +112,7 @@
123
  },
124
  {
125
  "cell_type": "code",
126
- "execution_count": 14,
127
  "metadata": {},
128
  "outputs": [],
129
  "source": [
@@ -161,7 +150,7 @@
161
  },
162
  {
163
  "cell_type": "code",
164
- "execution_count": 15,
165
  "metadata": {},
166
  "outputs": [],
167
  "source": [
@@ -204,7 +193,7 @@
204
  },
205
  {
206
  "cell_type": "code",
207
- "execution_count": 16,
208
  "metadata": {},
209
  "outputs": [],
210
  "source": [
@@ -226,40 +215,46 @@
226
  " prompt = ChatPromptTemplate.from_messages(\n",
227
  " [(\n",
228
  " \"system\",\n",
229
- " f\"\"\"# Knowledge Graph Instructions for GPT-4\n",
230
  "## 1. Overview\n",
231
- "You are a top-tier algorithm designed for extracting information in structured formats to build a knowledge graph.\n",
232
- "- **Nodes** represent entities and concepts. They're akin to Wikipedia nodes.\n",
233
- "- The aim is to achieve simplicity and clarity in the knowledge graph, making it accessible for a vast audience.\n",
 
234
  "## 2. Labeling Nodes\n",
235
- "- **Consistency**: Ensure you use basic or elementary types for node labels.\n",
236
- " - For example, when you identify an entity representing a person, always label it as **\"person\"**. Avoid using more specific terms like \"mathematician\" or \"scientist\".\n",
237
- "- **Node IDs**: Never utilize integers as node IDs. Node IDs should be names or human-readable identifiers found in the text.\n",
238
- "{'- **Allowed Node Labels:**' + \", \".join(allowed_nodes) if allowed_nodes else \"\"}\n",
239
- "{'- **Allowed Relationship Types**:' + \", \".join(allowed_rels) if allowed_rels else \"\"}\n",
 
 
240
  "## 3. Handling Numerical Data and Dates\n",
241
- "- Numerical data, like age or other related information, should be incorporated as attributes or properties of the respective nodes.\n",
242
- "- **No Separate Nodes for Dates/Numbers**: Do not create separate nodes for dates or numerical values. Always attach them as attributes or properties of nodes.\n",
243
- "- **Property Format**: Properties must be in a key-value format.\n",
244
- "- **Quotation Marks**: Never use escaped single or double quotes within property values.\n",
245
- "- **Naming Convention**: Use camelCase for property keys, e.g., `birthDate`.\n",
246
  "## 4. Coreference Resolution\n",
247
- "- **Maintain Entity Consistency**: When extracting entities, it's vital to ensure consistency.\n",
248
- "If an entity, such as \"John Doe\", is mentioned multiple times in the text but is referred to by different names or pronouns (e.g., \"Joe\", \"he\"),\n",
249
- "always use the most complete identifier for that entity throughout the knowledge graph. In this example, use \"John Doe\" as the entity ID.\n",
250
- "Remember, the knowledge graph should be coherent and easily understandable, so maintaining consistency in entity references is crucial.\n",
251
- "## 5. Strict Compliance\n",
252
- "Adhere to the rules strictly. Non-compliance will result in termination.\n",
253
- " \"\"\"),\n",
 
 
 
 
254
  " (\"human\", \"Use the given format to extract information from the following input: {input}\"),\n",
255
- " (\"human\", \"Tip: Make sure to answer in the correct format\"),\n",
256
  " ])\n",
257
  " return create_structured_output_chain(KnowledgeGraph, llm, prompt, verbose=False)"
258
  ]
259
  },
260
  {
261
  "cell_type": "code",
262
- "execution_count": 17,
263
  "metadata": {},
264
  "outputs": [],
265
  "source": [
@@ -282,7 +277,7 @@
282
  },
283
  {
284
  "cell_type": "code",
285
- "execution_count": 18,
286
  "metadata": {},
287
  "outputs": [],
288
  "source": [
@@ -292,71 +287,92 @@
292
  "# Read the wikipedia article\n",
293
  "raw_documents = WikipediaLoader(query=\"Chemotherapy\").load()\n",
294
  "# Define chunking strategy\n",
295
- "text_splitter = TokenTextSplitter(chunk_size=2048, chunk_overlap=24)\n",
296
  "\n",
297
  "# Only take the first the raw_documents\n",
298
- "documents = text_splitter.split_documents(raw_documents[:3])"
299
  ]
300
  },
301
  {
302
  "cell_type": "code",
303
- "execution_count": 19,
304
  "metadata": {},
305
  "outputs": [
306
  {
307
  "name": "stderr",
308
  "output_type": "stream",
309
  "text": [
310
- " 0%| | 0/3 [00:00<?, ?it/s]/local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain_core/_api/deprecation.py:119: LangChainDeprecationWarning: The function `create_structured_output_chain` was deprecated in LangChain 0.1.1 and will be removed in 0.2.0. Use create_structured_output_runnable instead.\n",
311
- " warn_deprecated(\n"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  ]
313
  },
314
  {
315
  "name": "stdout",
316
  "output_type": "stream",
317
  "text": [
318
- "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 429 Too Many Requests\"\n",
319
- "INFO:openai._base_client:Retrying request to /chat/completions in 0.931655 seconds\n",
320
- "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 429 Too Many Requests\"\n",
321
- "INFO:openai._base_client:Retrying request to /chat/completions in 1.853094 seconds\n",
322
- "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 429 Too Many Requests\"\n"
323
  ]
324
  },
325
  {
326
  "name": "stderr",
327
  "output_type": "stream",
328
  "text": [
329
- " 0%| | 0/3 [00:03<?, ?it/s]\n"
330
  ]
331
  },
332
  {
333
- "ename": "RateLimitError",
334
- "evalue": "Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}",
335
- "output_type": "error",
336
- "traceback": [
337
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
338
- "\u001b[0;31mRateLimitError\u001b[0m Traceback (most recent call last)",
339
- "Cell \u001b[0;32mIn[19], line 4\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtqdm\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tqdm\n\u001b[1;32m 3\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, d \u001b[38;5;129;01min\u001b[39;00m tqdm(\u001b[38;5;28menumerate\u001b[39m(documents), total\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mlen\u001b[39m(documents)):\n\u001b[0;32m----> 4\u001b[0m \u001b[43mextract_and_store_graph\u001b[49m\u001b[43m(\u001b[49m\u001b[43md\u001b[49m\u001b[43m)\u001b[49m\n",
340
- "Cell \u001b[0;32mIn[17], line 7\u001b[0m, in \u001b[0;36mextract_and_store_graph\u001b[0;34m(document, nodes, rels)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mextract_and_store_graph\u001b[39m(\n\u001b[1;32m 2\u001b[0m document: Document,\n\u001b[1;32m 3\u001b[0m nodes:Optional[List[\u001b[38;5;28mstr\u001b[39m]] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 4\u001b[0m rels:Optional[List[\u001b[38;5;28mstr\u001b[39m]]\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 5\u001b[0m \u001b[38;5;66;03m# Extract graph data using OpenAI functions\u001b[39;00m\n\u001b[1;32m 6\u001b[0m extract_chain \u001b[38;5;241m=\u001b[39m get_extraction_chain(nodes, rels)\n\u001b[0;32m----> 7\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[43mextract_chain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdocument\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpage_content\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mfunction\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[1;32m 8\u001b[0m \u001b[38;5;66;03m# Construct a graph document\u001b[39;00m\n\u001b[1;32m 9\u001b[0m graph_document \u001b[38;5;241m=\u001b[39m GraphDocument(\n\u001b[1;32m 10\u001b[0m nodes \u001b[38;5;241m=\u001b[39m [map_to_base_node(node) \u001b[38;5;28;01mfor\u001b[39;00m node \u001b[38;5;129;01min\u001b[39;00m data\u001b[38;5;241m.\u001b[39mnodes],\n\u001b[1;32m 11\u001b[0m relationships \u001b[38;5;241m=\u001b[39m [map_to_base_relationship(rel) \u001b[38;5;28;01mfor\u001b[39;00m rel \u001b[38;5;129;01min\u001b[39;00m data\u001b[38;5;241m.\u001b[39mrels],\n\u001b[1;32m 12\u001b[0m source \u001b[38;5;241m=\u001b[39m document\n\u001b[1;32m 13\u001b[0m )\n",
341
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain/chains/base.py:163\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m 161\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 162\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 163\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m 164\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m 166\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
342
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain/chains/base.py:153\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m 150\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 151\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m 152\u001b[0m outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 153\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 154\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m 155\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m 156\u001b[0m )\n\u001b[1;32m 158\u001b[0m final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m 159\u001b[0m inputs, outputs, return_only_outputs\n\u001b[1;32m 160\u001b[0m )\n\u001b[1;32m 161\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
343
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain/chains/llm.py:103\u001b[0m, in \u001b[0;36mLLMChain._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m 98\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_call\u001b[39m(\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 100\u001b[0m inputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any],\n\u001b[1;32m 101\u001b[0m run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 102\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Dict[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mstr\u001b[39m]:\n\u001b[0;32m--> 103\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 104\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcreate_outputs(response)[\u001b[38;5;241m0\u001b[39m]\n",
344
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain/chains/llm.py:115\u001b[0m, in \u001b[0;36mLLMChain.generate\u001b[0;34m(self, input_list, run_manager)\u001b[0m\n\u001b[1;32m 113\u001b[0m callbacks \u001b[38;5;241m=\u001b[39m run_manager\u001b[38;5;241m.\u001b[39mget_child() \u001b[38;5;28;01mif\u001b[39;00m run_manager \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 114\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm, BaseLanguageModel):\n\u001b[0;32m--> 115\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate_prompt\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 116\u001b[0m \u001b[43m \u001b[49m\u001b[43mprompts\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 117\u001b[0m \u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 118\u001b[0m \u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 119\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 120\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 121\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 122\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm\u001b[38;5;241m.\u001b[39mbind(stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm_kwargs)\u001b[38;5;241m.\u001b[39mbatch(\n\u001b[1;32m 123\u001b[0m cast(List, prompts), {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks}\n\u001b[1;32m 124\u001b[0m )\n",
345
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py:560\u001b[0m, in \u001b[0;36mBaseChatModel.generate_prompt\u001b[0;34m(self, prompts, stop, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m 552\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mgenerate_prompt\u001b[39m(\n\u001b[1;32m 553\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 554\u001b[0m prompts: List[PromptValue],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 557\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m 558\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m LLMResult:\n\u001b[1;32m 559\u001b[0m prompt_messages \u001b[38;5;241m=\u001b[39m [p\u001b[38;5;241m.\u001b[39mto_messages() \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m prompts]\n\u001b[0;32m--> 560\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprompt_messages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
346
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py:421\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m 419\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n\u001b[1;32m 420\u001b[0m run_managers[i]\u001b[38;5;241m.\u001b[39mon_llm_error(e, response\u001b[38;5;241m=\u001b[39mLLMResult(generations\u001b[38;5;241m=\u001b[39m[]))\n\u001b[0;32m--> 421\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m 422\u001b[0m flattened_outputs \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m 423\u001b[0m LLMResult(generations\u001b[38;5;241m=\u001b[39m[res\u001b[38;5;241m.\u001b[39mgenerations], llm_output\u001b[38;5;241m=\u001b[39mres\u001b[38;5;241m.\u001b[39mllm_output) \u001b[38;5;66;03m# type: ignore[list-item]\u001b[39;00m\n\u001b[1;32m 424\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results\n\u001b[1;32m 425\u001b[0m ]\n\u001b[1;32m 426\u001b[0m llm_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_combine_llm_outputs([res\u001b[38;5;241m.\u001b[39mllm_output \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results])\n",
347
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py:411\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m 408\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(messages):\n\u001b[1;32m 409\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 410\u001b[0m results\u001b[38;5;241m.\u001b[39mappend(\n\u001b[0;32m--> 411\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate_with_cache\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 412\u001b[0m \u001b[43m \u001b[49m\u001b[43mm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 413\u001b[0m \u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 414\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_managers\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_managers\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 415\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 416\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 417\u001b[0m )\n\u001b[1;32m 418\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 419\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n",
348
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py:632\u001b[0m, in \u001b[0;36mBaseChatModel._generate_with_cache\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m 630\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 631\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inspect\u001b[38;5;241m.\u001b[39msignature(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate)\u001b[38;5;241m.\u001b[39mparameters\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_manager\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m--> 632\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 633\u001b[0m \u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m 634\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 635\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 636\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate(messages, stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
349
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/langchain_openai/chat_models/base.py:548\u001b[0m, in \u001b[0;36mChatOpenAI._generate\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m 546\u001b[0m message_dicts, params \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_create_message_dicts(messages, stop)\n\u001b[1;32m 547\u001b[0m params \u001b[38;5;241m=\u001b[39m {\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mparams, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs}\n\u001b[0;32m--> 548\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmessages\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmessage_dicts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 549\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_create_chat_result(response)\n",
350
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/openai/_utils/_utils.py:277\u001b[0m, in \u001b[0;36mrequired_args.<locals>.inner.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 275\u001b[0m msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMissing required argument: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mquote(missing[\u001b[38;5;241m0\u001b[39m])\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 276\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[0;32m--> 277\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
351
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/openai/resources/chat/completions.py:581\u001b[0m, in \u001b[0;36mCompletions.create\u001b[0;34m(self, messages, model, frequency_penalty, function_call, functions, logit_bias, logprobs, max_tokens, n, presence_penalty, response_format, seed, stop, stream, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m 550\u001b[0m \u001b[38;5;129m@required_args\u001b[39m([\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m], [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[1;32m 551\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m 552\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 579\u001b[0m timeout: \u001b[38;5;28mfloat\u001b[39m \u001b[38;5;241m|\u001b[39m httpx\u001b[38;5;241m.\u001b[39mTimeout \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m|\u001b[39m NotGiven \u001b[38;5;241m=\u001b[39m NOT_GIVEN,\n\u001b[1;32m 580\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ChatCompletion \u001b[38;5;241m|\u001b[39m Stream[ChatCompletionChunk]:\n\u001b[0;32m--> 581\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 582\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/chat/completions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 583\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 584\u001b[0m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m 585\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmessages\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 586\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 587\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfrequency_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrequency_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 588\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunction_call\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunction_call\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 589\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunctions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunctions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 590\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogit_bias\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogit_bias\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 591\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 592\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 593\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mn\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 594\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mpresence_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mpresence_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 595\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mresponse_format\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mresponse_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 596\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseed\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 597\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstop\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 598\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 599\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtemperature\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 600\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtool_choice\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtool_choice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 601\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtools\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtools\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 602\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_logprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_logprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 603\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_p\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 604\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muser\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43muser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 605\u001b[0m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 606\u001b[0m \u001b[43m \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mCompletionCreateParams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 607\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 608\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 609\u001b[0m \u001b[43m \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\n\u001b[1;32m 610\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 611\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mChatCompletion\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 612\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 613\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mStream\u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatCompletionChunk\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 614\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
352
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/openai/_base_client.py:1232\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1218\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m 1219\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 1220\u001b[0m path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1227\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 1228\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m 1229\u001b[0m opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m 1230\u001b[0m method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[1;32m 1231\u001b[0m )\n\u001b[0;32m-> 1232\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
353
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/openai/_base_client.py:921\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 912\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrequest\u001b[39m(\n\u001b[1;32m 913\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 914\u001b[0m cast_to: Type[ResponseT],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 919\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 920\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[0;32m--> 921\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 922\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 923\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 924\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 925\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 926\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 927\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
354
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/openai/_base_client.py:997\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 995\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m 996\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m--> 997\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 998\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 999\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1000\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1001\u001b[0m \u001b[43m \u001b[49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1002\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1003\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1004\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1006\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m 1007\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m 1008\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
355
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/openai/_base_client.py:1045\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, remaining_retries, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1041\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m 1042\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m 1043\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1045\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1046\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1047\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1048\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1049\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1050\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1051\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
356
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/openai/_base_client.py:997\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 995\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m 996\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m--> 997\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 998\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 999\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1000\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1001\u001b[0m \u001b[43m \u001b[49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1002\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1003\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1004\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1006\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m 1007\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m 1008\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
357
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/openai/_base_client.py:1045\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, remaining_retries, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1041\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m 1042\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m 1043\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1045\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1046\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1047\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1048\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1049\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1050\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1051\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
358
- "File \u001b[0;32m~/miniconda3/envs/graph_rag/lib/python3.9/site-packages/openai/_base_client.py:1012\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1009\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m 1011\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1012\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1014\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[1;32m 1015\u001b[0m cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m 1016\u001b[0m options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1019\u001b[0m stream_cls\u001b[38;5;241m=\u001b[39mstream_cls,\n\u001b[1;32m 1020\u001b[0m )\n",
359
- "\u001b[0;31mRateLimitError\u001b[0m: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}"
360
  ]
361
  }
362
  ],
@@ -366,6 +382,71 @@
366
  "for i, d in tqdm(enumerate(documents), total=len(documents)):\n",
367
  " extract_and_store_graph(d)"
368
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
369
  }
370
  ],
371
  "metadata": {
 
2
  "cells": [
3
  {
4
  "cell_type": "code",
5
+ "execution_count": 1,
6
  "metadata": {},
7
  "outputs": [],
8
  "source": [
 
27
  },
28
  {
29
  "cell_type": "code",
30
+ "execution_count": 21,
31
  "metadata": {},
32
  "outputs": [
33
  {
 
37
  "Requirement already satisfied: langchain in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (0.1.16)\n",
38
  "Requirement already satisfied: neo4j in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (5.19.0)\n",
39
  "Requirement already satisfied: openai in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (1.23.2)\n",
40
+ "Requirement already satisfied: wikipedia in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (1.4.0)\n",
41
+ "Requirement already satisfied: tiktoken in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (0.6.0)\n",
42
+ "Requirement already satisfied: langchain_openai in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (0.1.3)\n",
 
 
 
43
  "Requirement already satisfied: PyYAML>=5.3 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from langchain) (6.0.1)\n",
44
  "Requirement already satisfied: SQLAlchemy<3,>=1.4 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from langchain) (2.0.29)\n",
45
  "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from langchain) (3.9.5)\n",
 
84
  "Requirement already satisfied: urllib3<3,>=1.21.1 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from requests<3,>=2->langchain) (2.2.1)\n",
85
  "Requirement already satisfied: greenlet!=0.4.17 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from SQLAlchemy<3,>=1.4->langchain) (3.0.3)\n",
86
  "Requirement already satisfied: soupsieve>1.2 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from beautifulsoup4->wikipedia) (2.5)\n",
87
+ "Requirement already satisfied: mypy-extensions>=0.3.0 in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain) (1.0.0)\n"
 
 
 
 
 
 
 
 
88
  ]
89
  }
90
  ],
 
94
  },
95
  {
96
  "cell_type": "code",
97
+ "execution_count": 2,
98
  "metadata": {},
99
  "outputs": [],
100
  "source": [
 
112
  },
113
  {
114
  "cell_type": "code",
115
+ "execution_count": 4,
116
  "metadata": {},
117
  "outputs": [],
118
  "source": [
 
150
  },
151
  {
152
  "cell_type": "code",
153
+ "execution_count": 5,
154
  "metadata": {},
155
  "outputs": [],
156
  "source": [
 
193
  },
194
  {
195
  "cell_type": "code",
196
+ "execution_count": 17,
197
  "metadata": {},
198
  "outputs": [],
199
  "source": [
 
215
  " prompt = ChatPromptTemplate.from_messages(\n",
216
  " [(\n",
217
  " \"system\",\n",
218
+ " f\"\"\"# Knowledge Graph Instructions for GPT-4\n",
219
  "## 1. Overview\n",
220
+ "You are a sophisticated algorithm tailored for parsing Wikipedia pages to construct a knowledge graph about chemotherapy and related cancer treatments.\n",
221
+ "- **Nodes** symbolize entities such as medical conditions, drugs, symptoms, treatments, and associated medical concepts.\n",
222
+ "- The goal is to create a precise and comprehensible knowledge graph, serving as a reliable resource for medical practitioners and scholarly research.\n",
223
+ "\n",
224
  "## 2. Labeling Nodes\n",
225
+ "- **Consistency**: Utilize uniform labels for node types to maintain clarity.\n",
226
+ " - For instance, consistently label drugs as **\"Drug\"**, symptoms as **\"Symptom\"**, and treatments as **\"Treatment\"**.\n",
227
+ "- **Node IDs**: Apply descriptive, legible identifiers for node IDs, sourced directly from the text.\n",
228
+ "\n",
229
+ "{'- **Allowed Node Labels:**' + \", \".join(['Drug', 'Symptom', 'Treatment', 'MedicalCondition', 'ResearchStudy']) if allowed_nodes else \"\"}\n",
230
+ "{'- **Allowed Relationship Types**:' + \", \".join(['Treats', 'Causes', 'Researches', 'Recommends']) if allowed_rels else \"\"}\n",
231
+ "\n",
232
  "## 3. Handling Numerical Data and Dates\n",
233
+ "- Integrate numerical data and dates as attributes of the corresponding nodes.\n",
234
+ "- **No Isolated Nodes for Dates/Numbers**: Directly associate dates and numerical figures as attributes with pertinent nodes.\n",
235
+ "- **Property Format**: Follow a straightforward key-value pattern for properties, with keys in camelCase, for example, `approvedYear`, `dosageAmount`.\n",
236
+ "\n",
 
237
  "## 4. Coreference Resolution\n",
238
+ "- **Entity Consistency**: Guarantee uniform identification of each entity across the graph.\n",
239
+ " - For example, if \"Methotrexate\" and \"MTX\" reference the same medication, uniformly apply \"Methotrexate\" as the node ID.\n",
240
+ "\n",
241
+ "## 5. Relationship Naming Conventions\n",
242
+ "- **Clarity and Standardization**: Utilize clear and standardized relationship names, preferring uppercase with underscores for readability.\n",
243
+ " - For instance, use \"HAS_SIDE_EFFECT\" instead of \"HASSIDEEFFECT\", use \"CAN_RESULT_FROM\" instead of \"CANRESULTFROM\" etc.\n",
244
+ "- **Relevance and Specificity**: Choose relationship names that accurately reflect the connection between nodes, such as \"INHIBITS\" or \"ACTIVATES\" for interactions between substances.\n",
245
+ "\n",
246
+ "## 6. Strict Compliance\n",
247
+ "Rigorous adherence to these instructions is essential. Failure to comply with the specified formatting and labeling norms will necessitate output revision or discard.\n",
248
+ " \"\"\"),\n",
249
  " (\"human\", \"Use the given format to extract information from the following input: {input}\"),\n",
250
+ " (\"human\", \"Tip: Precision in the node and relationship creation is vital for the integrity of the knowledge graph.\"),\n",
251
  " ])\n",
252
  " return create_structured_output_chain(KnowledgeGraph, llm, prompt, verbose=False)"
253
  ]
254
  },
255
  {
256
  "cell_type": "code",
257
+ "execution_count": 18,
258
  "metadata": {},
259
  "outputs": [],
260
  "source": [
 
277
  },
278
  {
279
  "cell_type": "code",
280
+ "execution_count": 21,
281
  "metadata": {},
282
  "outputs": [],
283
  "source": [
 
287
  "# Read the wikipedia article\n",
288
  "raw_documents = WikipediaLoader(query=\"Chemotherapy\").load()\n",
289
  "# Define chunking strategy\n",
290
+ "text_splitter = TokenTextSplitter(chunk_size=4096, chunk_overlap=96)\n",
291
  "\n",
292
  "# Only take the first the raw_documents\n",
293
+ "documents = text_splitter.split_documents(raw_documents[:5])"
294
  ]
295
  },
296
  {
297
  "cell_type": "code",
298
+ "execution_count": 22,
299
  "metadata": {},
300
  "outputs": [
301
  {
302
  "name": "stderr",
303
  "output_type": "stream",
304
  "text": [
305
+ " 0%| | 0/5 [00:00<?, ?it/s]"
306
+ ]
307
+ },
308
+ {
309
+ "name": "stdout",
310
+ "output_type": "stream",
311
+ "text": [
312
+ "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
313
+ ]
314
+ },
315
+ {
316
+ "name": "stderr",
317
+ "output_type": "stream",
318
+ "text": [
319
+ " 20%|β–ˆβ–ˆ | 1/5 [01:11<04:45, 71.44s/it]"
320
+ ]
321
+ },
322
+ {
323
+ "name": "stdout",
324
+ "output_type": "stream",
325
+ "text": [
326
+ "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
327
+ ]
328
+ },
329
+ {
330
+ "name": "stderr",
331
+ "output_type": "stream",
332
+ "text": [
333
+ " 40%|β–ˆβ–ˆβ–ˆβ–ˆ | 2/5 [01:25<01:53, 37.82s/it]"
334
+ ]
335
+ },
336
+ {
337
+ "name": "stdout",
338
+ "output_type": "stream",
339
+ "text": [
340
+ "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
341
+ ]
342
+ },
343
+ {
344
+ "name": "stderr",
345
+ "output_type": "stream",
346
+ "text": [
347
+ " 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 3/5 [01:33<00:48, 24.24s/it]"
348
  ]
349
  },
350
  {
351
  "name": "stdout",
352
  "output_type": "stream",
353
  "text": [
354
+ "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
 
 
 
 
355
  ]
356
  },
357
  {
358
  "name": "stderr",
359
  "output_type": "stream",
360
  "text": [
361
+ " 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 4/5 [01:49<00:20, 20.99s/it]"
362
  ]
363
  },
364
  {
365
+ "name": "stdout",
366
+ "output_type": "stream",
367
+ "text": [
368
+ "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
369
+ ]
370
+ },
371
+ {
372
+ "name": "stderr",
373
+ "output_type": "stream",
374
+ "text": [
375
+ "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5/5 [01:52<00:00, 22.58s/it]\n"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  ]
377
  }
378
  ],
 
382
  "for i, d in tqdm(enumerate(documents), total=len(documents)):\n",
383
  " extract_and_store_graph(d)"
384
  ]
385
+ },
386
+ {
387
+ "cell_type": "code",
388
+ "execution_count": 14,
389
+ "metadata": {},
390
+ "outputs": [],
391
+ "source": [
392
+ "# Query the knowledge graph in a RAG application\n",
393
+ "from langchain.chains import GraphCypherQAChain\n",
394
+ "\n",
395
+ "graph.refresh_schema()\n",
396
+ "\n",
397
+ "cypher_chain = GraphCypherQAChain.from_llm(\n",
398
+ " graph=graph,\n",
399
+ " cypher_llm=ChatOpenAI(temperature=0, model=\"gpt-4\"),\n",
400
+ " qa_llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-16k\"),\n",
401
+ " validate_cypher=True, # Validate relationship directions\n",
402
+ " verbose=True\n",
403
+ ")"
404
+ ]
405
+ },
406
+ {
407
+ "cell_type": "code",
408
+ "execution_count": 23,
409
+ "metadata": {},
410
+ "outputs": [
411
+ {
412
+ "name": "stdout",
413
+ "output_type": "stream",
414
+ "text": [
415
+ "\n",
416
+ "\n",
417
+ "\u001b[1m> Entering new GraphCypherQAChain chain...\u001b[0m\n",
418
+ "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n",
419
+ "Generated Cypher:\n",
420
+ "\u001b[32;1m\u001b[1;3mMATCH (c:Condition {name: \"Cancer\"})-[:CANRESULTFROM]->(t:Treatment) RETURN t.name\u001b[0m\n",
421
+ "Full Context:\n",
422
+ "\u001b[32;1m\u001b[1;3m[]\u001b[0m\n",
423
+ "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n",
424
+ "\n",
425
+ "\u001b[1m> Finished chain.\u001b[0m\n"
426
+ ]
427
+ },
428
+ {
429
+ "data": {
430
+ "text/plain": [
431
+ "{'query': 'What are the different treatment strategies for cancer?',\n",
432
+ " 'result': \"I'm sorry, but I don't have the information to answer that question.\"}"
433
+ ]
434
+ },
435
+ "execution_count": 23,
436
+ "metadata": {},
437
+ "output_type": "execute_result"
438
+ }
439
+ ],
440
+ "source": [
441
+ "cypher_chain.invoke({\"query\": \"What are the different treatment strategies for cancer?\"})"
442
+ ]
443
+ },
444
+ {
445
+ "cell_type": "code",
446
+ "execution_count": null,
447
+ "metadata": {},
448
+ "outputs": [],
449
+ "source": []
450
  }
451
  ],
452
  "metadata": {