{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "6e9a4f41",
   "metadata": {},
   "source": [
    "<div style=\"background-color:#000;\"><img src=\"pqn.png\"></img></div>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fd709f5c",
   "metadata": {},
   "source": [
    "This code integrates LangChain library functionalities to process and query PDF documents using OpenAI's language model. It loads a PDF file, splits it into pages, and stores these pages in a vector database (ChromaDB). It then creates a toolkit to interact with the vector store and uses an agent executor to query the database based on user input. This is useful for extracting and querying information from structured documents like financial reports."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "58bade97",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ce47c00a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import OpenAI\n",
    "from langchain.document_loaders import PyPDFLoader\n",
    "from langchain.vectorstores import Chroma\n",
    "from langchain.agents.agent_toolkits import (\n",
    "    create_vectorstore_agent,\n",
    "    VectorStoreToolkit,\n",
    "    VectorStoreInfo,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "18b8f141",
   "metadata": {},
   "source": [
    "Set the OpenAI API key for authentication"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7a0ddde1",
   "metadata": {},
   "outputs": [],
   "source": [
    "os.environ[\"OPENAI_API_KEY\"] = \"\"\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9cb3ca7c",
   "metadata": {},
   "source": [
    "Create an instance of the OpenAI language model with specified parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "396ba311",
   "metadata": {},
   "outputs": [
    {
     "ename": "AuthenticationError",
     "evalue": "Error code: 401 - {'error': {'message': 'Incorrect API key provided: sk-nzJ5u***************************************N1s3. You can find your API key at https://platform.openai.com/account/api-keys.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}}",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAuthenticationError\u001b[0m                       Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[20], line 9\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mopenai\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m OpenAI\n\u001b[1;32m      4\u001b[0m client \u001b[38;5;241m=\u001b[39m OpenAI(\n\u001b[1;32m      5\u001b[0m     \u001b[38;5;66;03m# This is the default and can be omitted\u001b[39;00m\n\u001b[1;32m      6\u001b[0m     api_key\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msk-nzJ5uA1io2NoFJNj6Z67T3BlbkFJr0ictKLQNDqKkEsCN1s3\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m      7\u001b[0m )\n\u001b[0;32m----> 9\u001b[0m chat_completion \u001b[38;5;241m=\u001b[39m \u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mchat\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompletions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     10\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmessages\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\n\u001b[1;32m     11\u001b[0m \u001b[43m        \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m     12\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrole\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\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\n\u001b[1;32m     13\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcontent\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mSay this is a test\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     14\u001b[0m \u001b[43m        \u001b[49m\u001b[43m}\u001b[49m\n\u001b[1;32m     15\u001b[0m \u001b[43m    \u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     16\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mgpt-3.5-turbo\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     17\u001b[0m \u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/openai/_utils/_utils.py:274\u001b[0m, in \u001b[0;36mrequired_args.<locals>.inner.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    272\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    273\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[0;32m--> 274\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~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/openai/resources/chat/completions.py:815\u001b[0m, in \u001b[0;36mCompletions.create\u001b[0;34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, presence_penalty, response_format, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m    775\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    776\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m    777\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    812\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    813\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[1;32m    814\u001b[0m     validate_response_format(response_format)\n\u001b[0;32m--> 815\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    816\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    817\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    818\u001b[0m \u001b[43m            \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m    819\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    820\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    821\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43maudio\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43maudio\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    822\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    823\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    824\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    825\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    826\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    827\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_completion_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_completion_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    828\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    829\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmetadata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    830\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodalities\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodalities\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    831\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    832\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mparallel_tool_calls\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mparallel_tool_calls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    833\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    834\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    835\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    836\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mservice_tier\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mservice_tier\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    837\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    838\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstore\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstore\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    839\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    840\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    841\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    842\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    843\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    844\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    845\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    846\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    847\u001b[0m \u001b[43m            \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    848\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    849\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    850\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    851\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    852\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    853\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    854\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    855\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    856\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/openai/_base_client.py:1277\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   1263\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m   1264\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1265\u001b[0m     path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1272\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   1273\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   1274\u001b[0m     opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m   1275\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   1276\u001b[0m     )\n\u001b[0;32m-> 1277\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~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/openai/_base_client.py:954\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    951\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    952\u001b[0m     retries_taken \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n\u001b[0;32m--> 954\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    955\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    956\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    957\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    958\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    959\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    960\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/openai/_base_client.py:1058\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1055\u001b[0m         err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m   1057\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-> 1058\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   1060\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   1061\u001b[0m     cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m   1062\u001b[0m     options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1066\u001b[0m     retries_taken\u001b[38;5;241m=\u001b[39mretries_taken,\n\u001b[1;32m   1067\u001b[0m )\n",
      "\u001b[0;31mAuthenticationError\u001b[0m: Error code: 401 - {'error': {'message': 'Incorrect API key provided: sk-nzJ5u***************************************N1s3. You can find your API key at https://platform.openai.com/account/api-keys.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}}"
     ]
    }
   ],
   "source": [
    "import os\n",
    "from openai import OpenAI\n",
    "\n",
    "client = OpenAI(\n",
    "    # This is the default and can be omitted\n",
    "    api_key=\"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\",\n",
    ")\n",
    "\n",
    "chat_completion = client.chat.completions.create(\n",
    "    messages=[\n",
    "        {\n",
    "            \"role\": \"user\",\n",
    "            \"content\": \"Say this is a test\",\n",
    "        }\n",
    "    ],\n",
    "    model=\"gpt-3.5-turbo\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6ebf63b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0.1, verbose=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e5e50726",
   "metadata": {},
   "source": [
    "Initialize a PDF loader for the specified file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "681ccbf2",
   "metadata": {},
   "outputs": [],
   "source": [
    "loader = PyPDFLoader(\"apple.pdf\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "41e538eb",
   "metadata": {},
   "source": [
    "Split the PDF into individual pages for processing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "adf3f45c",
   "metadata": {},
   "outputs": [],
   "source": [
    "pages = loader.load_and_split()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fbbc170b",
   "metadata": {},
   "source": [
    "Load the split pages into a Chroma vector database for efficient querying"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "964eaa4a",
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "You must provide an embedding function to compute embeddings.https://docs.trychroma.com/guides/embeddings",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[14], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m store \u001b[38;5;241m=\u001b[39m \u001b[43mChroma\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_documents\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcollection_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mannualreport\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/langchain_community/vectorstores/chroma.py:878\u001b[0m, in \u001b[0;36mChroma.from_documents\u001b[0;34m(cls, documents, embedding, ids, collection_name, persist_directory, client_settings, client, collection_metadata, **kwargs)\u001b[0m\n\u001b[1;32m    876\u001b[0m texts \u001b[38;5;241m=\u001b[39m [doc\u001b[38;5;241m.\u001b[39mpage_content \u001b[38;5;28;01mfor\u001b[39;00m doc \u001b[38;5;129;01min\u001b[39;00m documents]\n\u001b[1;32m    877\u001b[0m metadatas \u001b[38;5;241m=\u001b[39m [doc\u001b[38;5;241m.\u001b[39mmetadata \u001b[38;5;28;01mfor\u001b[39;00m doc \u001b[38;5;129;01min\u001b[39;00m documents]\n\u001b[0;32m--> 878\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_texts\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    879\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtexts\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtexts\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    880\u001b[0m \u001b[43m    \u001b[49m\u001b[43membedding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43membedding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    881\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmetadatas\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadatas\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    882\u001b[0m \u001b[43m    \u001b[49m\u001b[43mids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    883\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcollection_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcollection_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    884\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpersist_directory\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpersist_directory\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    885\u001b[0m \u001b[43m    \u001b[49m\u001b[43mclient_settings\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mclient_settings\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    886\u001b[0m \u001b[43m    \u001b[49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    887\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcollection_metadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcollection_metadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    888\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    889\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/langchain_community/vectorstores/chroma.py:842\u001b[0m, in \u001b[0;36mChroma.from_texts\u001b[0;34m(cls, texts, embedding, metadatas, ids, collection_name, persist_directory, client_settings, client, collection_metadata, **kwargs)\u001b[0m\n\u001b[1;32m    836\u001b[0m         chroma_collection\u001b[38;5;241m.\u001b[39madd_texts(\n\u001b[1;32m    837\u001b[0m             texts\u001b[38;5;241m=\u001b[39mbatch[\u001b[38;5;241m3\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m batch[\u001b[38;5;241m3\u001b[39m] \u001b[38;5;28;01melse\u001b[39;00m [],\n\u001b[1;32m    838\u001b[0m             metadatas\u001b[38;5;241m=\u001b[39mbatch[\u001b[38;5;241m2\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m batch[\u001b[38;5;241m2\u001b[39m] \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    839\u001b[0m             ids\u001b[38;5;241m=\u001b[39mbatch[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m    840\u001b[0m         )\n\u001b[1;32m    841\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 842\u001b[0m     \u001b[43mchroma_collection\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43madd_texts\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtexts\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtexts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadatas\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadatas\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mids\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    843\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m chroma_collection\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/langchain_community/vectorstores/chroma.py:313\u001b[0m, in \u001b[0;36mChroma.add_texts\u001b[0;34m(self, texts, metadatas, ids, **kwargs)\u001b[0m\n\u001b[1;32m    311\u001b[0m             \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(e\u001b[38;5;241m.\u001b[39margs[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m msg)\n\u001b[1;32m    312\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 313\u001b[0m             \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    314\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m empty_ids:\n\u001b[1;32m    315\u001b[0m     texts_without_metadatas \u001b[38;5;241m=\u001b[39m [texts[j] \u001b[38;5;28;01mfor\u001b[39;00m j \u001b[38;5;129;01min\u001b[39;00m empty_ids]\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/langchain_community/vectorstores/chroma.py:299\u001b[0m, in \u001b[0;36mChroma.add_texts\u001b[0;34m(self, texts, metadatas, ids, **kwargs)\u001b[0m\n\u001b[1;32m    297\u001b[0m ids_with_metadata \u001b[38;5;241m=\u001b[39m [ids[idx] \u001b[38;5;28;01mfor\u001b[39;00m idx \u001b[38;5;129;01min\u001b[39;00m non_empty_ids]\n\u001b[1;32m    298\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 299\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_collection\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mupsert\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    300\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmetadatas\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadatas\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    301\u001b[0m \u001b[43m        \u001b[49m\u001b[43membeddings\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43membeddings_with_metadatas\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    302\u001b[0m \u001b[43m        \u001b[49m\u001b[43mdocuments\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtexts_with_metadatas\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    303\u001b[0m \u001b[43m        \u001b[49m\u001b[43mids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mids_with_metadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    304\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    305\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    306\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mExpected metadata value to be\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mstr\u001b[39m(e):\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/chromadb/api/models/Collection.py:298\u001b[0m, in \u001b[0;36mCollection.upsert\u001b[0;34m(self, ids, embeddings, metadatas, documents, images, uris)\u001b[0m\n\u001b[1;32m    267\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mupsert\u001b[39m(\n\u001b[1;32m    268\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    269\u001b[0m     ids: OneOrMany[ID],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    279\u001b[0m     uris: Optional[OneOrMany[URI]] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    280\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    281\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Update the embeddings, metadatas or documents for provided ids, or create them if they don't exist.\u001b[39;00m\n\u001b[1;32m    282\u001b[0m \n\u001b[1;32m    283\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    290\u001b[0m \u001b[38;5;124;03m        None\u001b[39;00m\n\u001b[1;32m    291\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[1;32m    292\u001b[0m     (\n\u001b[1;32m    293\u001b[0m         ids,\n\u001b[1;32m    294\u001b[0m         embeddings,\n\u001b[1;32m    295\u001b[0m         metadatas,\n\u001b[1;32m    296\u001b[0m         documents,\n\u001b[1;32m    297\u001b[0m         uris,\n\u001b[0;32m--> 298\u001b[0m     ) \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_and_prepare_upsert_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    299\u001b[0m \u001b[43m        \u001b[49m\u001b[43mids\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43membeddings\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadatas\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdocuments\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mimages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43muris\u001b[49m\n\u001b[1;32m    300\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    302\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_client\u001b[38;5;241m.\u001b[39m_upsert(\n\u001b[1;32m    303\u001b[0m         collection_id\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mid,\n\u001b[1;32m    304\u001b[0m         ids\u001b[38;5;241m=\u001b[39mids,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    308\u001b[0m         uris\u001b[38;5;241m=\u001b[39muris,\n\u001b[1;32m    309\u001b[0m     )\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/chromadb/api/models/CollectionCommon.py:546\u001b[0m, in \u001b[0;36mCollectionCommon._validate_and_prepare_upsert_request\u001b[0;34m(self, ids, embeddings, metadatas, documents, images, uris)\u001b[0m\n\u001b[1;32m    544\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m embeddings \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    545\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m documents \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 546\u001b[0m         embeddings \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_embed\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdocuments\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    547\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    548\u001b[0m         embeddings \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_embed(\u001b[38;5;28minput\u001b[39m\u001b[38;5;241m=\u001b[39mimages)\n",
      "File \u001b[0;32m~/Documents/Development/python/strategy-lab1/.venv/lib/python3.10/site-packages/chromadb/api/models/CollectionCommon.py:577\u001b[0m, in \u001b[0;36mCollectionCommon._embed\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    575\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_embed\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Embeddings:\n\u001b[1;32m    576\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_embedding_function \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 577\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    578\u001b[0m             \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou must provide an embedding function to compute embeddings.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    579\u001b[0m             \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhttps://docs.trychroma.com/guides/embeddings\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    580\u001b[0m         )\n\u001b[1;32m    581\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_embedding_function(\u001b[38;5;28minput\u001b[39m\u001b[38;5;241m=\u001b[39m\u001b[38;5;28minput\u001b[39m)\n",
      "\u001b[0;31mValueError\u001b[0m: You must provide an embedding function to compute embeddings.https://docs.trychroma.com/guides/embeddings"
     ]
    }
   ],
   "source": [
    "store = Chroma.from_documents(pages, collection_name=\"annualreport\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dbd9b7f5",
   "metadata": {},
   "source": [
    "Create a VectorStoreInfo object to hold metadata about the vector store"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4fd45821",
   "metadata": {},
   "outputs": [],
   "source": [
    "vectorstore_info = VectorStoreInfo(\n",
    "    name=\"apple\",\n",
    "    description=\"Apple quarterly consolidated financials\",\n",
    "    vectorstore=store,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9db55c3d",
   "metadata": {},
   "source": [
    "Convert the vector store information into a toolkit for LangChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "40f81c28",
   "metadata": {},
   "outputs": [],
   "source": [
    "toolkit = VectorStoreToolkit(vectorstore_info=vectorstore_info)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "288a7fd0",
   "metadata": {},
   "source": [
    "Create an agent executor that uses the language model and toolkit for querying"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2bee8094",
   "metadata": {},
   "outputs": [],
   "source": [
    "agent_executor = create_vectorstore_agent(llm=llm, toolkit=toolkit, verbose=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "961d1da5",
   "metadata": {},
   "source": [
    "Prompt the user to enter a search term for querying the document"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "445ea906",
   "metadata": {},
   "outputs": [],
   "source": [
    "prompt = input(\"Enter your search term: \")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "c6b36ac3",
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'agent_executor' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[13], line 5\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m prompt:\n\u001b[1;32m      2\u001b[0m \n\u001b[1;32m      3\u001b[0m     \u001b[38;5;66;03m# Pass the user input to the agent executor for processing\u001b[39;00m\n\u001b[0;32m----> 5\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[43magent_executor\u001b[49m\u001b[38;5;241m.\u001b[39mrun(prompt)\n\u001b[1;32m      7\u001b[0m     \u001b[38;5;66;03m# Print the response from the language model to the screen\u001b[39;00m\n\u001b[1;32m      9\u001b[0m     \u001b[38;5;28mprint\u001b[39m(response)\n",
      "\u001b[0;31mNameError\u001b[0m: name 'agent_executor' is not defined"
     ]
    }
   ],
   "source": [
    "if prompt:\n",
    "\n",
    "    # Pass the user input to the agent executor for processing\n",
    "\n",
    "    response = agent_executor.run(prompt)\n",
    "\n",
    "    # Print the response from the language model to the screen\n",
    "\n",
    "    print(response)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8a4cac29",
   "metadata": {},
   "source": [
    "<a href=\"https://pyquantnews.com/\">PyQuant News</a> is where finance practitioners level up with Python for quant finance, algorithmic trading, and market data analysis. Looking to get started? Check out the fastest growing, top-selling course to <a href=\"https://gettingstartedwithpythonforquantfinance.com/\">get started with Python for quant finance</a>. For educational purposes. Not investment advise. Use at your own risk."
   ]
  }
 ],
 "metadata": {
  "jupytext": {
   "cell_metadata_filter": "-all",
   "main_language": "python",
   "notebook_metadata_filter": "-all"
  },
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}