{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "dfe37963-1af6-44fc-a841-8e462443f5e6",
   "metadata": {},
   "source": [
    "## Personal Knowledge Worker for Sameer Khadatkar\n",
    "\n",
    "This project will use RAG (Retrieval Augmented Generation) to ensure our question/answering assistant has high accuracy.\n",
    "\n",
    "This first implementation will use a simple, brute-force type of RAG.."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ba2779af-84ef-4227-9e9e-6eaf0df87e77",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "\n",
    "import os\n",
    "import glob\n",
    "from dotenv import load_dotenv\n",
    "import gradio as gr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "802137aa-8a74-45e0-a487-d1974927d7ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports for langchain, plotly and Chroma\n",
    "\n",
    "from langchain.document_loaders import DirectoryLoader, TextLoader\n",
    "from langchain.text_splitter import CharacterTextSplitter\n",
    "from langchain.schema import Document\n",
    "from langchain_openai import OpenAIEmbeddings, ChatOpenAI\n",
    "from langchain_chroma import Chroma\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.manifold import TSNE\n",
    "import numpy as np\n",
    "import plotly.graph_objects as go\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "from langchain.chains import ConversationalRetrievalChain\n",
    "from langchain.embeddings import HuggingFaceEmbeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "58c85082-e417-4708-9efe-81a5d55d1424",
   "metadata": {},
   "outputs": [],
   "source": [
    "# price is a factor, so we're going to use a low cost model\n",
    "\n",
    "MODEL = \"gpt-4o-mini\"\n",
    "db_name = \"vector_db\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ee78efcb-60fe-449e-a944-40bab26261af",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load environment variables in a file called .env\n",
    "\n",
    "load_dotenv(override=True)\n",
    "os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "730711a9-6ffe-4eee-8f48-d6cfb7314905",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read in documents using LangChain's loaders\n",
    "# Take everything in all the sub-folders of our knowledgebase\n",
    "\n",
    "folders = glob.glob(\"sameer-db/*\")\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",
    "documents = []\n",
    "for folder in folders:\n",
    "    doc_type = os.path.basename(folder)\n",
    "    loader = DirectoryLoader(folder, glob=\"**/*.md\", loader_cls=TextLoader, loader_kwargs=text_loader_kwargs)\n",
    "    folder_docs = loader.load()\n",
    "    documents.extend([add_metadata(doc, doc_type) for doc in folder_docs])\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\"Document types found: {set(doc.metadata['doc_type'] for doc in documents)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "78998399-ac17-4e28-b15f-0b5f51e6ee23",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Put the chunks of data into a Vector Store that associates a Vector Embedding with each chunk\n",
    "# Chroma is a popular open source Vector Database based on SQLLite\n",
    "\n",
    "embeddings = OpenAIEmbeddings()\n",
    "\n",
    "if os.path.exists(db_name):\n",
    "    Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()\n",
    "\n",
    "# Create vectorstore\n",
    "vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)\n",
    "print(f\"Vectorstore created with {vectorstore._collection.count()} documents\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ff2e7687-60d4-4920-a1d7-a34b9f70a250",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Let's investigate the vectors\n",
    "\n",
    "collection = vectorstore._collection\n",
    "count = collection.count()\n",
    "\n",
    "sample_embedding = collection.get(limit=1, include=[\"embeddings\"])[\"embeddings\"][0]\n",
    "dimensions = len(sample_embedding)\n",
    "print(f\"There are {count:,} vectors with {dimensions:,} dimensions in the vector store\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b0d45462-a818-441c-b010-b85b32bcf618",
   "metadata": {},
   "source": [
    "## Visualizing the Vector Store\n",
    "\n",
    "Let's take a minute to look at the documents and their embedding vectors to see what's going on."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b98adf5e-d464-4bd2-9bdf-bc5b6770263b",
   "metadata": {},
   "outputs": [],
   "source": [
    "result = collection.get(include=['embeddings', 'documents', 'metadatas'])\n",
    "vectors = np.array(result['embeddings'])\n",
    "documents = result['documents']\n",
    "metadatas = result['metadatas']\n",
    "doc_types = [metadata['doc_type'] for metadata in metadatas]\n",
    "colors = [['green', 'red'][['personal', 'profile'].index(t)] for t in doc_types]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "427149d5-e5d8-4abd-bb6f-7ef0333cca21",
   "metadata": {},
   "outputs": [],
   "source": [
    "# We humans find it easier to visalize things in 2D!\n",
    "# Reduce the dimensionality of the vectors to 2D using t-SNE\n",
    "# (t-distributed stochastic neighbor embedding)\n",
    "\n",
    "tsne = TSNE(n_components=2, random_state=42,perplexity=5)\n",
    "reduced_vectors = tsne.fit_transform(vectors)\n",
    "\n",
    "# Create the 2D scatter plot\n",
    "fig = go.Figure(data=[go.Scatter(\n",
    "    x=reduced_vectors[:, 0],\n",
    "    y=reduced_vectors[:, 1],\n",
    "    mode='markers',\n",
    "    marker=dict(size=5, color=colors, opacity=0.8),\n",
    "    text=[f\"Type: {t}<br>Text: {d[:100]}...\" for t, d in zip(doc_types, documents)],\n",
    "    hoverinfo='text'\n",
    ")])\n",
    "\n",
    "fig.update_layout(\n",
    "    title='2D Chroma Vector Store Visualization',\n",
    "    scene=dict(xaxis_title='x',yaxis_title='y'),\n",
    "    width=800,\n",
    "    height=600,\n",
    "    margin=dict(r=20, b=10, l=10, t=40)\n",
    ")\n",
    "\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e1418e88-acd5-460a-bf2b-4e6efc88e3dd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Let's try 3D!\n",
    "\n",
    "tsne = TSNE(n_components=3, random_state=42,perplexity=5)\n",
    "reduced_vectors = tsne.fit_transform(vectors)\n",
    "\n",
    "# Create the 3D scatter plot\n",
    "fig = go.Figure(data=[go.Scatter3d(\n",
    "    x=reduced_vectors[:, 0],\n",
    "    y=reduced_vectors[:, 1],\n",
    "    z=reduced_vectors[:, 2],\n",
    "    mode='markers',\n",
    "    marker=dict(size=5, color=colors, opacity=0.8),\n",
    "    text=[f\"Type: {t}<br>Text: {d[:100]}...\" for t, d in zip(doc_types, documents)],\n",
    "    hoverinfo='text'\n",
    ")])\n",
    "\n",
    "fig.update_layout(\n",
    "    title='3D Chroma Vector Store Visualization',\n",
    "    scene=dict(xaxis_title='x', yaxis_title='y', zaxis_title='z'),\n",
    "    width=900,\n",
    "    height=700,\n",
    "    margin=dict(r=20, b=10, l=10, t=40)\n",
    ")\n",
    "\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9468860b-86a2-41df-af01-b2400cc985be",
   "metadata": {},
   "source": [
    "## Time to use LangChain to bring it all together"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b3942a10-9977-4ae7-9acf-968c43ad0d4a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.schema import SystemMessage"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "45c0fb93-0a16-4e55-857b-1f9fd61ec24c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# create a new Chat with OpenAI\n",
    "llm = ChatOpenAI(temperature=0.7, model_name=MODEL)\n",
    "\n",
    "# set up the conversation memory for the chat\n",
    "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
    "memory.chat_memory.messages.insert(0, SystemMessage(\n",
    "    content=\"\"\"You are an AI Assistant specialized in providing accurate information about Sameer Khadatkar. Only respond when the question explicitly asks for information. \n",
    "    Keep your answers brief, factual, and based solely on the information provided. Do not speculate or fabricate details. \n",
    "    For example, if the user simply says \"hi,\" respond with: \"How can I help you?\"\n",
    "    \"\"\"\n",
    "))\n",
    "\n",
    "# the retriever is an abstraction over the VectorStore that will be used during RAG\n",
    "retriever = vectorstore.as_retriever(k=4)\n",
    "\n",
    "# putting it together: set up the conversation chain with the GPT 3.5 LLM, the vector store and memory\n",
    "conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "968e7bf2-e862-4679-a11f-6c1efb6ec8ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Let's try a simple question\n",
    "\n",
    "query = \"Who are you?\"\n",
    "result = conversation_chain.invoke({\"question\": query})\n",
    "print(result[\"answer\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5b5a9013-d5d4-4e25-9e7c-cdbb4f33e319",
   "metadata": {},
   "outputs": [],
   "source": [
    "# set up a new conversation memory for the chat\n",
    "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
    "\n",
    "# putting it together: set up the conversation chain with the GPT 4o-mini LLM, the vector store and memory\n",
    "conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bbbcb659-13ce-47ab-8a5e-01b930494964",
   "metadata": {},
   "source": [
    "## Now we will bring this up in Gradio using the Chat interface -\n",
    "\n",
    "A quick and easy way to prototype a chat with an LLM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c3536590-85c7-4155-bd87-ae78a1467670",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Wrapping that in a function\n",
    "\n",
    "def chat(question, history):\n",
    "    result = conversation_chain.invoke({\"question\": question})\n",
    "    return result[\"answer\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b252d8c1-61a8-406d-b57a-8f708a62b014",
   "metadata": {},
   "outputs": [],
   "source": [
    "# And in Gradio:\n",
    "\n",
    "view = gr.ChatInterface(chat, type=\"messages\").launch(inbrowser=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e23270cf-2d46-4f9e-aeb3-de1673900d2f",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3476931e-7d94-4b4d-8cc6-67a1bd5fa79c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}