{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "\n",
    "import os\n",
    "import glob\n",
    "from dotenv import load_dotenv\n",
    "import gradio as gr\n",
    "# import gemini\n",
    "import google.generativeai"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports for langchain\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",
    "from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI\n",
    "import numpy as np\n",
    "from sklearn.manifold import TSNE\n",
    "import plotly.graph_objects as go\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "from langchain.chains import ConversationalRetrievalChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# price is a factor for our company, so we're going to use a low cost model\n",
    "\n",
    "MODEL = \"gemini-1.5-flash\"\n",
    "db_name = \"vector_db\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load environment variables in a file called .env\n",
    "\n",
    "load_dotenv()\n",
    "os.environ['GOOGLE_API_KEY'] = os.getenv('GOOGLE_API_KEY', 'your-key-if-not-using-env')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "google.generativeai.configure()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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(\"knowledge-base/*\")\n",
    "\n",
    "# With thanks to CG and Jon R, students on the course, for this fix needed for some users \n",
    "text_loader_kwargs = {'encoding': 'utf-8'}\n",
    "# If that doesn't work, some Windows users might need to uncomment the next line instead\n",
    "# text_loader_kwargs={'autodetect_encoding': True}\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",
    "    for doc in folder_docs:\n",
    "        doc.metadata[\"doc_type\"] = doc_type\n",
    "        documents.append(doc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Created a chunk of size 1088, which is longer than the specified 1000\n"
     ]
    }
   ],
   "source": [
    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
    "chunks = text_splitter.split_documents(documents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "123"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(chunks)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Document types found: company, contracts, employees, products\n"
     ]
    }
   ],
   "source": [
    "doc_types = set(chunk.metadata['doc_type'] for chunk in chunks)\n",
    "print(f\"Document types found: {', '.join(doc_types)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Vectorstore created with 123 documents\n"
     ]
    }
   ],
   "source": [
    "embeddings = GoogleGenerativeAIEmbeddings(model=\"models/embedding-001\")\n",
    "\n",
    "# Check if a Chroma Datastore already exists - if so, delete the collection to start from scratch\n",
    "\n",
    "if os.path.exists(db_name):\n",
    "    Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()\n",
    "\n",
    "# Create our Chroma vectorstore!\n",
    "\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": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The vectors have 768 dimensions\n"
     ]
    }
   ],
   "source": [
    "# Get one vector and find how many dimensions it has\n",
    "\n",
    "collection = vectorstore._collection\n",
    "sample_embedding = collection.get(limit=1, include=[\"embeddings\"])[\"embeddings\"][0]\n",
    "dimensions = len(sample_embedding)\n",
    "print(f\"The vectors have {dimensions:,} dimensions\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Prework\n",
    "\n",
    "result = collection.get(include=['embeddings', 'documents', 'metadatas'])\n",
    "vectors = np.array(result['embeddings'])\n",
    "documents = result['documents']\n",
    "doc_types = [metadata['doc_type'] for metadata in result['metadatas']]\n",
    "colors = [['blue', 'green', 'red', 'orange'][['products', 'employees', 'contracts', 'company'].index(t)] for t in doc_types]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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)\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,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Let's try 3D!\n",
    "\n",
    "tsne = TSNE(n_components=3, random_state=42)\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",
   "metadata": {},
   "source": [
    "RAG pipeline using langchain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\GANESH\\AppData\\Local\\Temp\\ipykernel_524\\4130109764.py:5: LangChainDeprecationWarning:\n",
      "\n",
      "Please see the migration guide at: https://python.langchain.com/docs/versions/migrating_memory/\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# create a new Chat with ChatGoogleGenerativeAI\n",
    "llm = ChatGoogleGenerativeAI(model=MODEL, temperature=0.7)\n",
    "\n",
    "# set up the conversation memory for the chat\n",
    "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
    "\n",
    "# the retriever is an abstraction over the VectorStore that will be used during RAG\n",
    "retriever = vectorstore.as_retriever()\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": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Insurellm is an insurance technology company with 200 employees and over 300 clients worldwide.  They offer four software products, including Homellm, a portal for home insurance companies that integrates with existing platforms and offers a customer portal for policy management.  Their pricing model is based on provider size and customization needs.\n"
     ]
    }
   ],
   "source": [
    "query = \"Can you describe Insurellm in a few sentences\"\n",
    "result = conversation_chain.invoke({\"question\":query})\n",
    "print(result[\"answer\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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",
   "metadata": {},
   "source": [
    "Gradio User Interface"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "def chat(message, history):\n",
    "    result = conversation_chain.invoke({\"question\": message})\n",
    "    return result[\"answer\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "* Running on local URL:  http://127.0.0.1:7860\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "view = gr.ChatInterface(chat, type=\"messages\").launch(inbrowser=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "llms",
   "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": 2
}