{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Create Vector database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from dotenv import load_dotenv\n",
    "import google.generativeai as genai\n",
    "from langchain_anthropic import ChatAnthropic\n",
    "from langchain_community.vectorstores.faiss import FAISS\n",
    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
    "from langchain_google_genai import GoogleGenerativeAIEmbeddings\n",
    "from langchain.text_splitter import RecursiveCharacterTextSplitter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "load_dotenv()\n",
    "genai.configure(api_key=os.getenv(\"GOOGLE_API_KEY\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_text_chunks(text):\n",
    "    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)\n",
    "    chunks = text_splitter.split_text(text)\n",
    "    return chunks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_vector_store(text_chunks):\n",
    "    embeddings = GoogleGenerativeAIEmbeddings(model = \"models/embedding-001\")\n",
    "    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)\n",
    "    vector_store.save_local(\"faiss_index\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"all_hotels.txt\", \"r\", encoding=\"utf8\") as file:\n",
    "    text = file.read()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "chunks = get_text_chunks(text)\n",
    "get_vector_store(chunks)"
   ]
  }
 ],
 "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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}