{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
    "from langchain_core.runnables import RunnablePassthrough\n",
    "import os\n",
    "from dotenv import load_dotenv\n",
    "load_dotenv()\n",
    "from langchain_community.document_loaders import WebBaseLoader\n",
    "from langchain.vectorstores import FAISS\n",
    "from langchain_core.output_parsers import StrOutputParser"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "from IPython.display import Markdown\n",
    "def to_Markdown(text):\n",
    "    return Markdown(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
    "def VectorStore(data,embedding):\n",
    "    splitter = RecursiveCharacterTextSplitter(chunk_size = 1000,chunk_overlap =500)\n",
    "    chunks = splitter.split_documents(data)\n",
    "    vector = FAISS.from_documents(chunks,embedding)\n",
    "    retriever = vector.as_retriever()\n",
    "    return retriever\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = ChatGoogleGenerativeAI(model='gemini-1.5-flash')\n",
    "from langchain_huggingface import HuggingFaceEmbeddings\n",
    "embedding = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Hi there! How can I help you today?'"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm.invoke(\"hi\").content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "def data_ingestion(path):\n",
    "    loader = WebBaseLoader(path)  \n",
    "    data = loader.load()\n",
    "    return data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts import ChatPromptTemplate\n",
    "def prompt_helper():\n",
    "    template = \"\"\" Answer Based on the following context:\n",
    "    {context}\n",
    "    Question: {question}\n",
    "    provide only helpful information.\n",
    "    \"\"\"\n",
    "    prompt = ChatPromptTemplate.from_template(template)\n",
    "    return prompt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "def main():\n",
    "    path = input(\"Enter the website link: \")\n",
    "    data = data_ingestion(path)\n",
    "    retriever = VectorStore(data,embedding)\n",
    "    prompt = prompt_helper()\n",
    "    chain = (\n",
    "    {'context': retriever , 'question': RunnablePassthrough()}\n",
    "    | prompt\n",
    "    |llm\n",
    "    |StrOutputParser()\n",
    "    )\n",
    "    question = input(\"Enter the question from the link: \")\n",
    "    response = chain.invoke(question)\n",
    "    print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The provided text does not contain any information about the color blue.\n"
     ]
    }
   ],
   "source": [
    "main()"
   ]
  },
  {
   "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": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}