LangChain_01.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h1>imports</h1>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "from langchain.llms.openai import OpenAI\n",
    "\n",
    "from langchain.agents import create_sql_agent\n",
    "from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
    "from langchain.agents import AgentExecutor\n",
    "\n",
    "from langchain.sql_database import SQLDatabase\n",
    "\n",
    "from dotenv import load_dotenv # pip install load-dotenv\n",
    "load_dotenv()\n",
    "\n",
    "import psycopg2 # pip install psycopg-binary\n",
    "\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h1>Connect to SQL and create an Agent</h1>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<langchain.sql_database.SQLDatabase object at 0x7f1dd74f1310>\n"
     ]
    }
   ],
   "source": [
    "db = SQLDatabase.from_uri('postgresql+psycopg2://admin:password123@localhost/admin')\n",
    "print(db)\n",
    "\n",
    "from langchain.chat_models import ChatOpenAI\n",
    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
    "\n",
    "     \n",
    "\n",
    "toolkit = SQLDatabaseToolkit(db=db,llm=llm)\n",
    "\n",
    "agent_executor = create_sql_agent(\n",
    "    llm=llm,\n",
    "    toolkit=toolkit,\n",
    "    verbose=True\n",
    ")\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h1>Run agent to ask OpenAI for answer</h1>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
      "Action Input: \"\"\u001b[0m\n",
      "Observation: \u001b[38;5;200m\u001b[1;3mteachers, people\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI should use the teachers table to find the first_name and last_name columns and calculate the mean salary.\n",
      "Action: query_sql_db\n",
      "Action Input: \"SELECT first_name, last_name FROM teachers WHERE salary < (SELECT AVG(salary) FROM teachers) ORDER BY salary ASC LIMIT 10\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m[('Janet', 'Smith'), ('Samantha', 'Bush'), ('Kathleen', 'Roush'), ('Samuel', 'Cole'), ('Betty', 'Diaz')]\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI have found the first_name and last_name of teachers who earn less than the mean salary and ordered them by salary in ascending order.\n",
      "Final Answer: The first_name and last_name of teachers who earn less than the mean salary are Janet Smith, Samantha Bush, Kathleen Roush, Samuel Cole, and Betty Diaz.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The first_name and last_name of teachers who earn less than the mean salary are Janet Smith, Samantha Bush, Kathleen Roush, Samuel Cole, and Betty Diaz.'"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.run(\"using the teachers table, find the first_name and last name of teachers who earn less the mean salary?\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}