LLM_Engineering_OLD/week5/community-contributions/tochi/whatsapp_chat_rag.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "300ea30a",
   "metadata": {},
   "source": [
    "# Expert Knowledge Worker\n",
    "### This project is a question and answering agent based of exported WhatsApp chat messages in from a group chat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4bc17177",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "\n",
    "import os\n",
    "import glob\n",
    "from dotenv import load_dotenv\n",
    "import gradio as gr\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "400ac859",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports fomr langchain\n",
    "\n",
    "from langchain.document_loaders import DirectoryLoader, TextLoader\n",
    "from langchain.text_splitter import CharacterTextSplitter\n",
    "from langchain_openai import OpenAIEmbeddings, ChatOpenAI\n",
    "from langchain_chroma import Chroma\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "from langchain.chains import ConversationalRetrievalChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "22199256",
   "metadata": {},
   "outputs": [],
   "source": [
    "# importing the low cost model and database\n",
    "\n",
    "MODEL = \"gpt-5-nano\"\n",
    "db_name = \"vector_db\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9f6be1f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "load_dotenv(override=True)\n",
    "os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b62754d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read in documents using LangChain's loaders\n",
    "# Take only .txt files in the knowledge-base folder (not subfolders)\n",
    "\n",
    "files = glob.glob(\"knowledge-base/*.txt\")\n",
    "\n",
    "print(files)\n",
    "\n",
    "def add_metadata(doc, doc_type):\n",
    "    doc.metadata[\"doc_type\"] = doc_type\n",
    "    return doc\n",
    "\n",
    "text_loader_kwargs = {'encoding': 'utf-8'}\n",
    "\n",
    "# Load all .txt files from knowledge-base folder\n",
    "doc_type = \"knowledge-base\"\n",
    "loader = DirectoryLoader(\n",
    "    \"knowledge-base\", \n",
    "    glob=\"*.txt\",  # Only .txt files in root folder, not subfolders\n",
    "    loader_cls=TextLoader, \n",
    "    loader_kwargs=text_loader_kwargs\n",
    ")\n",
    "documents = loader.load()\n",
    "\n",
    "# Add metadata to all documents\n",
    "documents = [add_metadata(doc, doc_type) for doc in documents]\n",
    "\n",
    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
    "chunks = text_splitter.split_documents(documents)\n",
    "\n",
    "print(f\"Total number of chunks: {len(chunks)}\")\n",
    "print(f\"Total number of documents: {len(documents)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "63aeac25",
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = OpenAIEmbeddings()\n",
    "if os.path.exists(db_name):\n",
    "    Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()\n",
    "\n",
    "\n",
    "vectorstore = Chroma.from_documents(\n",
    "    documents=chunks, embedding=embeddings, persist_directory=db_name\n",
    ")\n",
    "print(f\"Vectorstore created with {vectorstore._collection.count()} documents\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5426899a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# create a new Chat with OpenAI\n",
    "llm = ChatOpenAI(temperature=0.7, model_name=MODEL)\n",
    "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
    "retriever = vectorstore.as_retriever()\n",
    "conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "87e0e7c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "query = \"Who is mentioned a lot?\"\n",
    "result = conversation_chain.invoke({\"question\": query})\n",
    "print(result[\"answer\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f36bac2f",
   "metadata": {},
   "outputs": [],
   "source": [
    "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
    "conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1e087213",
   "metadata": {},
   "outputs": [],
   "source": [
    "def chat(question, history):\n",
    "    result = conversation_chain.invoke({\"question\": question})\n",
    "    return result[\"answer\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e1fd9b2d",
   "metadata": {},
   "outputs": [],
   "source": [
    "view = gr.ChatInterface(chat, type=\"messages\").launch(inbrowser=True)"
   ]
  }
 ],
 "metadata": {
  "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}