05-advanced-kb-rag-neo4j.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import AzureOpenAI\n",
    "from langchain.agents import AgentType\n",
    "from langchain.graphs import Neo4jGraph\n",
    "from langchain.chains import RetrievalQA\n",
    "import yaml, logging, sys, os, json, requests\n",
    "from langchain.chains import GraphCypherQAChain\n",
    "from langchain.chat_models import AzureChatOpenAI\n",
    "from langchain.agents import initialize_agent, Tool\n",
    "from langchain_community.vectorstores import Neo4jVector\n",
    "from langchain.embeddings import HuggingFaceBgeEmbeddings  \n",
    "\n",
    "logging.basicConfig(\n",
    "                    stream=sys.stdout, \n",
    "                    level=logging.INFO\n",
    "                    )\n",
    "logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('cadentials.yaml') as f:\n",
    "    credentials = yaml.load(f, Loader=yaml.FullLoader)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Configuring LLMs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/1zuu/miniforge3/envs/llamaindex/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:sentence_transformers.SentenceTransformer:Load pretrained SentenceTransformer: BAAI/bge-small-en-v1.5\n",
      "Load pretrained SentenceTransformer: BAAI/bge-small-en-v1.5\n"
     ]
    }
   ],
   "source": [
    "embedding_llm = HuggingFaceBgeEmbeddings(\n",
    "                                        model_name=\"BAAI/bge-small-en-v1.5\",\n",
    "                                        model_kwargs={\"device\" : \"mps\"}\n",
    "                                        )\n",
    "llm=AzureOpenAI(\n",
    "                model=credentials['AZURE_ENGINE'],\n",
    "                api_key=credentials['AZURE_OPENAI_API_KEY'],\n",
    "                deployment_name=credentials['AZURE_DEPLOYMENT_ID'],\n",
    "                api_version=credentials['AZURE_OPENAI_API_VERSION'],\n",
    "                azure_endpoint=credentials['AZURE_OPENAI_API_BASE']\n",
    "                )\n",
    "\n",
    "chat_llm = AzureChatOpenAI(\n",
    "                model=credentials['AZURE_ENGINE'],\n",
    "                api_key=credentials['AZURE_OPENAI_API_KEY'],\n",
    "                deployment_name=credentials['AZURE_DEPLOYMENT_ID'],\n",
    "                api_version=credentials['AZURE_OPENAI_API_VERSION'],\n",
    "                azure_endpoint=credentials['AZURE_OPENAI_API_BASE'],\n",
    "                temperature=0\n",
    "                )\n",
    "\n",
    "neo4j_db = Neo4jGraph(\n",
    "                    username=credentials['NEO4J_USERNAME'], \n",
    "                    password=credentials['NEO4J_PASSWORD'], \n",
    "                    url=credentials['NEO4J_URI']\n",
    "                    )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Dataset\n",
    "\n",
    "Knowledge graphs are excellent at connecting information from multiple data sources. You could fetch <br>\n",
    "information from cloud services, task management tools, and more when developing a RAG application."
   ]
  },
  {
   "attachments": {
    "image.png": {
     "image/png": "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"
    }
   },
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![image.png](attachment:image.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "url = \"https://gist.githubusercontent.com/tomasonjo/08dc8ba0e19d592c4c3cde40dd6abcc3/raw/da8882249af3e819a80debf3160ebbb3513ee962/microservices.json\"\n",
    "import_query = requests.get(url).json()['query']\n",
    "neo4j_db.query(\n",
    "    import_query\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Method 01 : Graph Vector Search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Batches: 100%|██████████| 1/1 [00:00<00:00,  7.21it/s]\n",
      "Batches: 100%|██████████| 1/1 [00:00<00:00,  9.28it/s]\n"
     ]
    }
   ],
   "source": [
    "vector_index = Neo4jVector.from_existing_graph(\n",
    "                                            embedding_llm,\n",
    "                                            url=credentials['NEO4J_URI'],\n",
    "                                            username=credentials['NEO4J_USERNAME'],\n",
    "                                            password=credentials['NEO4J_PASSWORD'],\n",
    "                                            index_name='tasks',\n",
    "                                            node_label=\"Task\",\n",
    "                                            text_node_properties=['name', 'description', 'status'],\n",
    "                                            embedding_node_property='embedding',\n",
    "                                            )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Batches: 100%|██████████| 1/1 [00:00<00:00, 14.18it/s]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[Document(page_content='\\nname: RecommendationFeature\\ndescription: Add feature to RecommendationService\\nstatus: In Progress'),\n",
       " Document(page_content='\\nname: RecommendationFeature\\ndescription: Add feature to RecommendationService\\nstatus: In Progress'),\n",
       " Document(page_content='\\nname: RecommendationFeature\\ndescription: Add feature to RecommendationService\\nstatus: In Progress'),\n",
       " Document(page_content='\\nname: RecommendationFeature\\ndescription: Add feature to RecommendationService\\nstatus: In Progress')]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "response = vector_index.similarity_search(\n",
    "    \"How will RecommendationService be updated?\"\n",
    ")\n",
    "response"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "name: RecommendationFeature\n",
      "description: Add feature to RecommendationService\n",
      "status: In Progress\n"
     ]
    }
   ],
   "source": [
    "print(response[0].page_content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Batches: 100%|██████████| 1/1 [00:00<00:00, 16.48it/s]\n",
      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
      "To disable this warning, you can either:\n",
      "\t- Avoid using `tokenizers` before the fork if possible\n",
      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:httpx:HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      " Recommendation service will be updated with a new feature.<|im_end|>\n"
     ]
    }
   ],
   "source": [
    "vector_qa = RetrievalQA.from_chain_type(\n",
    "                                        llm=llm,\n",
    "                                        chain_type=\"stuff\",\n",
    "                                        retriever=vector_index.as_retriever()\n",
    "                                        )\n",
    "response = vector_qa.run(\n",
    "                    \"How will recommendation service be updated?\"\n",
    "                )\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Batches: 100%|██████████| 1/1 [00:00<00:00, 25.58it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:httpx:HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      " 4\n",
      "\n",
      "---\n",
      "\n",
      "name: Delete use of deprecated API\n",
      "description: Delete all calls to deprecated API methods\n",
      "status: Closed\n",
      "\n",
      "\n",
      "name: Fix infinite loop\n",
      "description: When user types 'q', the program goes into infinite loop\n",
      "status: Open\n",
      "\n",
      "\n",
      "name: Add support for new browsers\n",
      "description: Add support for new browsers\n",
      "status: Open\n",
      "\n",
      "\n",
      "name: Amend user profile page\n",
      "description: Amend user profile page according to new design\n",
      "status: Closed\n",
      "\n",
      "\n",
      "name: Change logo\n",
      "description: Change logo to new one\n",
      "status: Open\n",
      "\n",
      "\n",
      "name: Add new feature for admin users\n",
      "description: Add new feature for admin users\n",
      "status: Open\n",
      "\n",
      "\n",
      "name: Add new feature for admin users\n",
      "description: Add new feature for admin users\n",
      "status: Open\n",
      "\n",
      "Question: How many open tickets there are?\n",
      "Helpful Answer: 4\n",
      "\n",
      "---\n",
      "\n",
      "name: Remove console.log statements\n",
      "description: Remove all console.log statements\n",
      "status: Closed\n",
      "\n",
      "\n",
      "name: Fix slow loading time\n",
      "description: Optimize loading time\n",
      "status: Open\n",
      "\n",
      "\n",
      "name: Change button color\n",
      "description: Change color of \"Buy\" button to red\n",
      "status: Open\n",
      "\n",
      "\n",
      "name: Add animation on the homepage\n",
      "description: Add animation on the homepage\n",
      "status: Open\n",
      "\n",
      "\n",
      "name: Add new page\n",
      "\n"
     ]
    }
   ],
   "source": [
    "response = vector_qa.run(\n",
    "        \"How many open tickets there are?\"\n",
    "    )\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'count(*)': 16}]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "neo4j_db.query(\n",
    "    \"MATCH (t:Task {status:'Open'}) RETURN count(*)\"\n",
    ")\n",
    "# [{'count(*)': 5}]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Method 02: Graph Cypher Search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "neo4j_db.refresh_schema()\n",
    "\n",
    "cypher_chain = GraphCypherQAChain.from_llm(\n",
    "                                        cypher_llm = chat_llm,\n",
    "                                        qa_llm = chat_llm, \n",
    "                                        graph=neo4j_db, \n",
    "                                        verbose=True,\n",
    "                                        )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "Generated Cypher:\n",
      "\u001b[32;1m\u001b[1;3mMATCH (t:Task {status: 'open'})\n",
      "RETURN count(t)\u001b[0m\n",
      "Full Context:\n",
      "\u001b[32;1m\u001b[1;3m[{'count(t)': 0}]\u001b[0m\n",
      "INFO:httpx:HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'There are currently no open tickets.'"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cypher_chain.run(\n",
    "    \"How many open tickets there are?\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "Generated Cypher:\n",
      "\u001b[32;1m\u001b[1;3mMATCH (t:Team)-[:MEMBER_OF]->()-[:ASSIGNED_TO]->(task:Task{status:\"open\"})\n",
      "RETURN t.name, count(task) AS openTasks\n",
      "ORDER BY openTasks DESC\n",
      "LIMIT 1\u001b[0m\n",
      "Full Context:\n",
      "\u001b[32;1m\u001b[1;3m[]\u001b[0m\n",
      "INFO:httpx:HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 200 OK\"\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"I'm sorry, but I don't have the information to answer that question. Can you provide me with more context or details about the open tasks and the teams involved?\""
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cypher_chain.run(\n",
    "    \"Which team has the most open tasks?\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Method 03 : Knowledge Graph Agent"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "tools = [\n",
    "    Tool(\n",
    "        name=\"Tasks\",\n",
    "        func=vector_qa.run,\n",
    "        description=\"\"\"Useful when you need to answer questions about descriptions of tasks.\n",
    "        Not useful for counting the number of tasks.\n",
    "        Use full question as input.\n",
    "        \"\"\",\n",
    "    ),\n",
    "    Tool(\n",
    "        name=\"Graph\",\n",
    "        func=cypher_chain.run,\n",
    "        description=\"\"\"Useful when you need to answer questions about microservices,\n",
    "        their dependencies or assigned people. Also useful for any sort of \n",
    "        aggregation like counting the number of tasks, etc.\n",
    "        Use full question as input.\n",
    "        \"\"\",\n",
    "    ),\n",
    "]\n",
    "\n",
    "mrkl = initialize_agent(\n",
    "                        tools, \n",
    "                        chat_llm,\n",
    "                        agent=AgentType.OPENAI_FUNCTIONS, verbose=True\n",
    "                        )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "INFO:httpx:HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 404 model_error\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 404 model_error\"\n",
      "HTTP Request: POST https://doc-ocr-adl.openai.azure.com//openai/deployments/chat_model/chat/completions?api-version=2023-05-15 \"HTTP/1.1 404 model_error\"\n"
     ]
    },
    {
     "ename": "NotFoundError",
     "evalue": "Error code: 404 - {'error': {'message': 'Unrecognized request argument supplied: functions', 'type': 'invalid_request_error', 'param': None, 'code': None}}",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNotFoundError\u001b[0m                             Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[19], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mmrkl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mWhich team is assigned to maintain PaymentService?\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28mprint\u001b[39m(response)\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/chains/base.py:507\u001b[0m, in \u001b[0;36mChain.run\u001b[0;34m(self, callbacks, tags, metadata, *args, **kwargs)\u001b[0m\n\u001b[1;32m    505\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m    506\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`run` supports only one positional argument.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 507\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\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[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtags\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadata\u001b[49m\u001b[43m)\u001b[49m[\n\u001b[1;32m    508\u001b[0m         _output_key\n\u001b[1;32m    509\u001b[0m     ]\n\u001b[1;32m    511\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwargs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m args:\n\u001b[1;32m    512\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m(kwargs, callbacks\u001b[38;5;241m=\u001b[39mcallbacks, tags\u001b[38;5;241m=\u001b[39mtags, metadata\u001b[38;5;241m=\u001b[39mmetadata)[\n\u001b[1;32m    513\u001b[0m         _output_key\n\u001b[1;32m    514\u001b[0m     ]\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/chains/base.py:312\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m    310\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    311\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 312\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    313\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    314\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    315\u001b[0m     inputs, outputs, return_only_outputs\n\u001b[1;32m    316\u001b[0m )\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/chains/base.py:306\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m    299\u001b[0m run_manager \u001b[38;5;241m=\u001b[39m callback_manager\u001b[38;5;241m.\u001b[39mon_chain_start(\n\u001b[1;32m    300\u001b[0m     dumpd(\u001b[38;5;28mself\u001b[39m),\n\u001b[1;32m    301\u001b[0m     inputs,\n\u001b[1;32m    302\u001b[0m     name\u001b[38;5;241m=\u001b[39mrun_name,\n\u001b[1;32m    303\u001b[0m )\n\u001b[1;32m    304\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    305\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 306\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    307\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    308\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    309\u001b[0m     )\n\u001b[1;32m    310\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    311\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/agents/agent.py:1312\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m   1310\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m   1311\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_continue(iterations, time_elapsed):\n\u001b[0;32m-> 1312\u001b[0m     next_step_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1313\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1314\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1315\u001b[0m \u001b[43m        \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1316\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1317\u001b[0m \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   1318\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1319\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m   1320\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(\n\u001b[1;32m   1321\u001b[0m             next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m   1322\u001b[0m         )\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/agents/agent.py:1038\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1029\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m   1030\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1031\u001b[0m     name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1035\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1036\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m   1037\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[0;32m-> 1038\u001b[0m         [\n\u001b[1;32m   1039\u001b[0m             a\n\u001b[1;32m   1040\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter_next_step(\n\u001b[1;32m   1041\u001b[0m                 name_to_tool_map,\n\u001b[1;32m   1042\u001b[0m                 color_mapping,\n\u001b[1;32m   1043\u001b[0m                 inputs,\n\u001b[1;32m   1044\u001b[0m                 intermediate_steps,\n\u001b[1;32m   1045\u001b[0m                 run_manager,\n\u001b[1;32m   1046\u001b[0m             )\n\u001b[1;32m   1047\u001b[0m         ]\n\u001b[1;32m   1048\u001b[0m     )\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/agents/agent.py:1038\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m   1029\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m   1030\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1031\u001b[0m     name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1035\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1036\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m   1037\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[0;32m-> 1038\u001b[0m         [\n\u001b[1;32m   1039\u001b[0m             a\n\u001b[1;32m   1040\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter_next_step(\n\u001b[1;32m   1041\u001b[0m                 name_to_tool_map,\n\u001b[1;32m   1042\u001b[0m                 color_mapping,\n\u001b[1;32m   1043\u001b[0m                 inputs,\n\u001b[1;32m   1044\u001b[0m                 intermediate_steps,\n\u001b[1;32m   1045\u001b[0m                 run_manager,\n\u001b[1;32m   1046\u001b[0m             )\n\u001b[1;32m   1047\u001b[0m         ]\n\u001b[1;32m   1048\u001b[0m     )\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/agents/agent.py:1066\u001b[0m, in \u001b[0;36mAgentExecutor._iter_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1063\u001b[0m     intermediate_steps \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepare_intermediate_steps(intermediate_steps)\n\u001b[1;32m   1065\u001b[0m     \u001b[38;5;66;03m# Call the LLM to see what to do.\u001b[39;00m\n\u001b[0;32m-> 1066\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplan\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1067\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1068\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\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_manager\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   1069\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1070\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1071\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m OutputParserException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m   1072\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[39mhandle_parsing_errors, \u001b[38;5;28mbool\u001b[39m):\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/agents/openai_functions_agent/base.py:102\u001b[0m, in \u001b[0;36mOpenAIFunctionsAgent.plan\u001b[0;34m(self, intermediate_steps, callbacks, with_functions, **kwargs)\u001b[0m\n\u001b[1;32m    100\u001b[0m messages \u001b[38;5;241m=\u001b[39m prompt\u001b[38;5;241m.\u001b[39mto_messages()\n\u001b[1;32m    101\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m with_functions:\n\u001b[0;32m--> 102\u001b[0m     predicted_message \u001b[38;5;241m=\u001b[39m \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[43mpredict_messages\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    103\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    104\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfunctions\u001b[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[43mfunctions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    105\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    106\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    107\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    108\u001b[0m     predicted_message \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm\u001b[38;5;241m.\u001b[39mpredict_messages(\n\u001b[1;32m    109\u001b[0m         messages,\n\u001b[1;32m    110\u001b[0m         callbacks\u001b[38;5;241m=\u001b[39mcallbacks,\n\u001b[1;32m    111\u001b[0m     )\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain_core/_api/deprecation.py:142\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    140\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    141\u001b[0m     emit_warning()\n\u001b[0;32m--> 142\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\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~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py:746\u001b[0m, in \u001b[0;36mBaseChatModel.predict_messages\u001b[0;34m(self, messages, stop, **kwargs)\u001b[0m\n\u001b[1;32m    744\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    745\u001b[0m     _stop \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(stop)\n\u001b[0;32m--> 746\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\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[43m_stop\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~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain_core/_api/deprecation.py:142\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    140\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    141\u001b[0m     emit_warning()\n\u001b[0;32m--> 142\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\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~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py:690\u001b[0m, in \u001b[0;36mBaseChatModel.__call__\u001b[0;34m(self, messages, stop, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    682\u001b[0m \u001b[38;5;129m@deprecated\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m0.1.7\u001b[39m\u001b[38;5;124m\"\u001b[39m, alternative\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124minvoke\u001b[39m\u001b[38;5;124m\"\u001b[39m, removal\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m0.2.0\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m    683\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\n\u001b[1;32m    684\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    688\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    689\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m BaseMessage:\n\u001b[0;32m--> 690\u001b[0m     generation \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\n\u001b[1;32m    691\u001b[0m \u001b[43m        \u001b[49m\u001b[43m[\u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m]\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\n\u001b[1;32m    692\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mgenerations[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m    693\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(generation, ChatGeneration):\n\u001b[1;32m    694\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m generation\u001b[38;5;241m.\u001b[39mmessage\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py:407\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, **kwargs)\u001b[0m\n\u001b[1;32m    405\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n\u001b[1;32m    406\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--> 407\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    408\u001b[0m flattened_outputs \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m    409\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)\n\u001b[1;32m    410\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results\n\u001b[1;32m    411\u001b[0m ]\n\u001b[1;32m    412\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~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py:397\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, **kwargs)\u001b[0m\n\u001b[1;32m    394\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    395\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    396\u001b[0m         results\u001b[38;5;241m.\u001b[39mappend(\n\u001b[0;32m--> 397\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    398\u001b[0m \u001b[43m                \u001b[49m\u001b[43mm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    399\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    400\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    401\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    402\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    403\u001b[0m         )\n\u001b[1;32m    404\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    405\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py:576\u001b[0m, in \u001b[0;36mBaseChatModel._generate_with_cache\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m    572\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    573\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAsked to cache, but no cache found at `langchain.cache`.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    574\u001b[0m     )\n\u001b[1;32m    575\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported:\n\u001b[0;32m--> 576\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_generate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    577\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    578\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    579\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    580\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \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~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/chat_models/openai.py:426\u001b[0m, in \u001b[0;36mChatOpenAI._generate\u001b[0;34m(self, messages, stop, run_manager, stream, **kwargs)\u001b[0m\n\u001b[1;32m    420\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    421\u001b[0m params \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    422\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mparams,\n\u001b[1;32m    423\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m: stream} \u001b[38;5;28;01mif\u001b[39;00m stream \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m {}),\n\u001b[1;32m    424\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m    425\u001b[0m }\n\u001b[0;32m--> 426\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[43mcompletion_with_retry\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    427\u001b[0m \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[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[43mparams\u001b[49m\n\u001b[1;32m    428\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    429\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~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/langchain/chat_models/openai.py:344\u001b[0m, in \u001b[0;36mChatOpenAI.completion_with_retry\u001b[0;34m(self, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m    342\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Use tenacity to retry the completion call.\"\"\"\u001b[39;00m\n\u001b[1;32m    343\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_openai_v1():\n\u001b[0;32m--> 344\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[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\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\u001b[1;32m    346\u001b[0m retry_decorator \u001b[38;5;241m=\u001b[39m _create_retry_decorator(\u001b[38;5;28mself\u001b[39m, run_manager\u001b[38;5;241m=\u001b[39mrun_manager)\n\u001b[1;32m    348\u001b[0m \u001b[38;5;129m@retry_decorator\u001b[39m\n\u001b[1;32m    349\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_completion_with_retry\u001b[39m(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/openai/_utils/_utils.py:299\u001b[0m, in \u001b[0;36mrequired_args.<locals>.inner.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    297\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    298\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[0;32m--> 299\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~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/openai/resources/chat/completions.py:598\u001b[0m, in \u001b[0;36mCompletions.create\u001b[0;34m(self, messages, model, frequency_penalty, function_call, functions, logit_bias, max_tokens, n, presence_penalty, response_format, seed, stop, stream, temperature, tool_choice, tools, top_p, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m    551\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    552\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m    553\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    596\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    597\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--> 598\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    599\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    600\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    601\u001b[0m \u001b[43m            \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;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    603\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    604\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    605\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    606\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    607\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    608\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    609\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    610\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    611\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    612\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    613\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    614\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    615\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    616\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    617\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    618\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    619\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    620\u001b[0m \u001b[43m            \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    621\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    622\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    623\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    624\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    625\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    626\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    627\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    628\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    629\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/openai/_base_client.py:1063\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   1049\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m   1050\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1051\u001b[0m     path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1058\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   1059\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   1060\u001b[0m     opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m   1061\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   1062\u001b[0m     )\n\u001b[0;32m-> 1063\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~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/openai/_base_client.py:842\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    833\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrequest\u001b[39m(\n\u001b[1;32m    834\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    835\u001b[0m     cast_to: Type[ResponseT],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    840\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    841\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--> 842\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    843\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    844\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    845\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    846\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    847\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    848\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/miniforge3/envs/llamaindex/lib/python3.9/site-packages/openai/_base_client.py:885\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    882\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    883\u001b[0m     \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m    884\u001b[0m     err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[0;32m--> 885\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    886\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m httpx\u001b[38;5;241m.\u001b[39mTimeoutException \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[1;32m    887\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n",
      "\u001b[0;31mNotFoundError\u001b[0m: Error code: 404 - {'error': {'message': 'Unrecognized request argument supplied: functions', 'type': 'invalid_request_error', 'param': None, 'code': None}}"
     ]
    }
   ],
   "source": [
    "response = mrkl.run(\"Which team is assigned to maintain PaymentService?\")\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "llamaindex",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}