{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import dotenv\n",
    "import os\n",
    "dotenv.load_dotenv('.env.rag')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_openai import ChatOpenAI\n",
    "llm = ChatOpenAI(model=\"gpt-4o-mini\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Mpox is a disease that spreads through close contact, including sexual contact, and can cause symptoms such as blistered skin rashes, ulcers, and flu-like symptoms. It has been present in the U.S. since 2022 and was declared a global health emergency by the WHO. Recently, a new strain of mpox, known as clade Ib, has emerged, primarily affecting regions in Africa.'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import bs4\n",
    "from langchain import hub\n",
    "from langchain_chroma import Chroma\n",
    "from langchain_community.document_loaders import TextLoader\n",
    "from langchain_core.output_parsers import StrOutputParser\n",
    "from langchain_core.runnables import RunnablePassthrough\n",
    "from langchain_openai import OpenAIEmbeddings\n",
    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
    "\n",
    "# Load, chunk and index the contents of the blog.\n",
    "folder = 'example_medical'\n",
    "docs = []\n",
    "\n",
    "for file in os.listdir(folder):\n",
    "    if file.endswith('.txt'):\n",
    "        loader = TextLoader(os.path.join(folder, file))\n",
    "        docs.extend(loader.load())\n",
    "\n",
    "\n",
    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
    "splits = text_splitter.split_documents(docs)\n",
    "vectorstore = Chroma.from_documents(documents=splits, embedding=OpenAIEmbeddings())\n",
    "\n",
    "# Retrieve and generate using the relevant snippets of the blog.\n",
    "retriever = vectorstore.as_retriever()\n",
    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
    "\n",
    "\n",
    "def format_docs(docs):\n",
    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
    "\n",
    "\n",
    "rag_chain = (\n",
    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
    "    | prompt\n",
    "    | llm\n",
    "    | StrOutputParser()\n",
    ")\n",
    "\n",
    "rag_chain.invoke(\"What is mpox?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}