{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import os\n",
    "from dotenv import load_dotenv\n",
    "from pyprojroot import here\n",
    "from langchain.chains import create_sql_query_chain\n",
    "from langchain_community.agent_toolkits import create_sql_agent\n",
    "from langchain_openai import ChatOpenAI\n",
    "from langchain_community.agent_toolkits.sql.toolkit import SQLDatabaseToolkit\n",
    "from langchain_community.utilities import SQLDatabase\n",
    "\n",
    "load_dotenv()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Set the environment variable and load the LLM**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "os.environ['OPENAI_API_KEY'] = os.getenv(\"OPEN_AI_API_KEY\")\n",
    "\n",
    "\n",
    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
    "# llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "# llm = ChatOpenAI(model=\"gpt-4o\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Load and test the sqlite db**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "sqlite\n",
      "['aircrafts_data', 'airports_data', 'boarding_passes', 'bookings', 'car_rentals', 'flights', 'hotels', 'seats', 'ticket_flights', 'tickets', 'trip_recommendations']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"[('773', 'Boeing 777-300', 11100), ('763', 'Boeing 767-300', 7900), ('SU9', 'Sukhoi Superjet-100', 3000), ('320', 'Airbus A320-200', 5700), ('321', 'Airbus A321-200', 5600), ('319', 'Airbus A319-100', 6700), ('733', 'Boeing 737-300', 4200), ('CN1', 'Cessna 208 Caravan', 1200), ('CR2', 'Bombardier CRJ-200', 2700)]\""
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sqldb_directory = here(\"data/travel.sqlite\")\n",
    "db = SQLDatabase.from_uri(f\"sqlite:///{sqldb_directory}\")\n",
    "print(db.dialect)\n",
    "print(db.get_usable_table_names())\n",
    "db.run(\"SELECT * FROM aircrafts_data LIMIT 10;\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Create the SQL agent and run a test query**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'SELECT COUNT(*) AS total_rows FROM aircrafts_data;'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain = create_sql_query_chain(llm, db)\n",
    "response = chain.invoke({\"question\": \"How many rows are there in the aircrafts_data table?\"})\n",
    "response"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'[(9,)]'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "db.run(response)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "rag-sqlagent",
   "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": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}