Updated KG Creation

kg_creation.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -27,7 +27,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -37,12 +37,9 @@
       "Requirement already satisfied: langchain in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (0.1.16)\n",
       "Requirement already satisfied: neo4j in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (5.19.0)\n",
       "Requirement already satisfied: openai in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (1.23.2)\n",
-      "Collecting wikipedia\n",
-      "  Downloading wikipedia-1.4.0.tar.gz (27 kB)\n",
-      "  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
-      "\u001b[?25hRequirement already satisfied: tiktoken in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (0.6.0)\n",
-      "Collecting langchain_openai\n",
-      "  Downloading langchain_openai-0.1.3-py3-none-any.whl.metadata (2.5 kB)\n",
+      "Requirement already satisfied: wikipedia in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (1.4.0)\n",
+      "Requirement already satisfied: tiktoken in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (0.6.0)\n",
+      "Requirement already satisfied: langchain_openai in /local/home/pbhandari/miniconda3/envs/graph_rag/lib/python3.9/site-packages (0.1.3)\n",
       "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",
       "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",
       "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 @@
       "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",
       "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",
       "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",
-      "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",
-      "Downloading langchain_openai-0.1.3-py3-none-any.whl (33 kB)\n",
-      "Building wheels for collected packages: wikipedia\n",
-      "  Building wheel for wikipedia (setup.py) ... \u001b[?25ldone\n",
-      "\u001b[?25h  Created wheel for wikipedia: filename=wikipedia-1.4.0-py3-none-any.whl size=11678 sha256=8579328fd821efddb0b23c1aed4bccd2d0f77a18118ee2e2a9e69badd2d5aa0d\n",
-      "  Stored in directory: /local/home/pbhandari/.cache/pip/wheels/c2/46/f4/caa1bee71096d7b0cdca2f2a2af45cacf35c5760bee8f00948\n",
-      "Successfully built wikipedia\n",
-      "Installing collected packages: wikipedia, langchain_openai\n",
-      "Successfully installed langchain_openai-0.1.3 wikipedia-1.4.0\n"
+      "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"
      ]
     }
    ],
@@ -105,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -123,7 +112,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -161,7 +150,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -204,7 +193,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -226,40 +215,46 @@
     "    prompt = ChatPromptTemplate.from_messages(\n",
     "        [(\n",
     "          \"system\",\n",
-    "          f\"\"\"# Knowledge Graph Instructions for GPT-4\n",
+    "        f\"\"\"# Knowledge Graph Instructions for GPT-4\n",
     "## 1. Overview\n",
-    "You are a top-tier algorithm designed for extracting information in structured formats to build a knowledge graph.\n",
-    "- **Nodes** represent entities and concepts. They're akin to Wikipedia nodes.\n",
-    "- The aim is to achieve simplicity and clarity in the knowledge graph, making it accessible for a vast audience.\n",
+    "You are a sophisticated algorithm tailored for parsing Wikipedia pages to construct a knowledge graph about chemotherapy and related cancer treatments.\n",
+    "- **Nodes** symbolize entities such as medical conditions, drugs, symptoms, treatments, and associated medical concepts.\n",
+    "- The goal is to create a precise and comprehensible knowledge graph, serving as a reliable resource for medical practitioners and scholarly research.\n",
+    "\n",
     "## 2. Labeling Nodes\n",
-    "- **Consistency**: Ensure you use basic or elementary types for node labels.\n",
-    "  - 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",
-    "- **Node IDs**: Never utilize integers as node IDs. Node IDs should be names or human-readable identifiers found in the text.\n",
-    "{'- **Allowed Node Labels:**' + \", \".join(allowed_nodes) if allowed_nodes else \"\"}\n",
-    "{'- **Allowed Relationship Types**:' + \", \".join(allowed_rels) if allowed_rels else \"\"}\n",
+    "- **Consistency**: Utilize uniform labels for node types to maintain clarity.\n",
+    "  - For instance, consistently label drugs as **\"Drug\"**, symptoms as **\"Symptom\"**, and treatments as **\"Treatment\"**.\n",
+    "- **Node IDs**: Apply descriptive, legible identifiers for node IDs, sourced directly from the text.\n",
+    "\n",
+    "{'- **Allowed Node Labels:**' + \", \".join(['Drug', 'Symptom', 'Treatment', 'MedicalCondition', 'ResearchStudy']) if allowed_nodes else \"\"}\n",
+    "{'- **Allowed Relationship Types**:' + \", \".join(['Treats', 'Causes', 'Researches', 'Recommends']) if allowed_rels else \"\"}\n",
+    "\n",
     "## 3. Handling Numerical Data and Dates\n",
-    "- Numerical data, like age or other related information, should be incorporated as attributes or properties of the respective nodes.\n",
-    "- **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",
-    "- **Property Format**: Properties must be in a key-value format.\n",
-    "- **Quotation Marks**: Never use escaped single or double quotes within property values.\n",
-    "- **Naming Convention**: Use camelCase for property keys, e.g., `birthDate`.\n",
+    "- Integrate numerical data and dates as attributes of the corresponding nodes.\n",
+    "- **No Isolated Nodes for Dates/Numbers**: Directly associate dates and numerical figures as attributes with pertinent nodes.\n",
+    "- **Property Format**: Follow a straightforward key-value pattern for properties, with keys in camelCase, for example, `approvedYear`, `dosageAmount`.\n",
+    "\n",
     "## 4. Coreference Resolution\n",
-    "- **Maintain Entity Consistency**: When extracting entities, it's vital to ensure consistency.\n",
-    "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",
-    "always use the most complete identifier for that entity throughout the knowledge graph. In this example, use \"John Doe\" as the entity ID.\n",
-    "Remember, the knowledge graph should be coherent and easily understandable, so maintaining consistency in entity references is crucial.\n",
-    "## 5. Strict Compliance\n",
-    "Adhere to the rules strictly. Non-compliance will result in termination.\n",
-    "          \"\"\"),\n",
+    "- **Entity Consistency**: Guarantee uniform identification of each entity across the graph.\n",
+    "  - For example, if \"Methotrexate\" and \"MTX\" reference the same medication, uniformly apply \"Methotrexate\" as the node ID.\n",
+    "\n",
+    "## 5. Relationship Naming Conventions\n",
+    "- **Clarity and Standardization**: Utilize clear and standardized relationship names, preferring uppercase with underscores for readability.\n",
+    "  - For instance, use \"HAS_SIDE_EFFECT\" instead of \"HASSIDEEFFECT\", use \"CAN_RESULT_FROM\" instead of \"CANRESULTFROM\" etc.\n",
+    "- **Relevance and Specificity**: Choose relationship names that accurately reflect the connection between nodes, such as \"INHIBITS\" or \"ACTIVATES\" for interactions between substances.\n",
+    "\n",
+    "## 6. Strict Compliance\n",
+    "Rigorous adherence to these instructions is essential. Failure to comply with the specified formatting and labeling norms will necessitate output revision or discard.\n",
+    "        \"\"\"),\n",
     "            (\"human\", \"Use the given format to extract information from the following input: {input}\"),\n",
-    "            (\"human\", \"Tip: Make sure to answer in the correct format\"),\n",
+    "            (\"human\", \"Tip: Precision in the node and relationship creation is vital for the integrity of the knowledge graph.\"),\n",
     "        ])\n",
     "    return create_structured_output_chain(KnowledgeGraph, llm, prompt, verbose=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -282,7 +277,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -292,71 +287,92 @@
     "# Read the wikipedia article\n",
     "raw_documents = WikipediaLoader(query=\"Chemotherapy\").load()\n",
     "# Define chunking strategy\n",
-    "text_splitter = TokenTextSplitter(chunk_size=2048, chunk_overlap=24)\n",
+    "text_splitter = TokenTextSplitter(chunk_size=4096, chunk_overlap=96)\n",
     "\n",
     "# Only take the first the raw_documents\n",
-    "documents = text_splitter.split_documents(raw_documents[:3])"
+    "documents = text_splitter.split_documents(raw_documents[:5])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "  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",
-      "  warn_deprecated(\n"
+      "  0%|          | 0/5 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 20%|██        | 1/5 [01:11<04:45, 71.44s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 40%|████      | 2/5 [01:25<01:53, 37.82s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 60%|██████    | 3/5 [01:33<00:48, 24.24s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 429 Too Many Requests\"\n",
-      "INFO:openai._base_client:Retrying request to /chat/completions in 0.931655 seconds\n",
-      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 429 Too Many Requests\"\n",
-      "INFO:openai._base_client:Retrying request to /chat/completions in 1.853094 seconds\n",
-      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 429 Too Many Requests\"\n"
+      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "  0%|          | 0/3 [00:03<?, ?it/s]\n"
+      " 80%|████████  | 4/5 [01:49<00:20, 20.99s/it]"
      ]
     },
     {
-     "ename": "RateLimitError",
-     "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'}}",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mRateLimitError\u001b[0m                            Traceback (most recent call last)",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "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",
-      "\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'}}"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 5/5 [01:52<00:00, 22.58s/it]\n"
      ]
     }
    ],
@@ -366,6 +382,71 @@
     "for i, d in tqdm(enumerate(documents), total=len(documents)):\n",
     "    extract_and_store_graph(d)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Query the knowledge graph in a RAG application\n",
+    "from langchain.chains import GraphCypherQAChain\n",
+    "\n",
+    "graph.refresh_schema()\n",
+    "\n",
+    "cypher_chain = GraphCypherQAChain.from_llm(\n",
+    "    graph=graph,\n",
+    "    cypher_llm=ChatOpenAI(temperature=0, model=\"gpt-4\"),\n",
+    "    qa_llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-16k\"),\n",
+    "    validate_cypher=True, # Validate relationship directions\n",
+    "    verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new GraphCypherQAChain chain...\u001b[0m\n",
+      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n",
+      "Generated Cypher:\n",
+      "\u001b[32;1m\u001b[1;3mMATCH (c:Condition {name: \"Cancer\"})-[:CANRESULTFROM]->(t:Treatment) RETURN t.name\u001b[0m\n",
+      "Full Context:\n",
+      "\u001b[32;1m\u001b[1;3m[]\u001b[0m\n",
+      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'query': 'What are the different treatment strategies for cancer?',\n",
+       " 'result': \"I'm sorry, but I don't have the information to answer that question.\"}"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cypher_chain.invoke({\"query\": \"What are the different treatment strategies for cancer?\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {