langchain/docs/modules/agents/plan_and_execute.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "406483c4",
   "metadata": {},
   "source": [
    "## Plan and Execute\n",
    "\n",
    "Plan and execute agents accomplish an objective by first planning what to do, then executing the sub tasks. This idea is largely inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) and then the [\"Plan-and-Solve\" paper](https://arxiv.org/abs/2305.04091).\n",
    "\n",
    "The planning is almost always done by an LLM.\n",
    "\n",
    "The execution is usually done by a separate agent (equipped with tools)."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "91192118",
   "metadata": {},
   "source": [
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6ccd1dc5",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.experimental.plan_and_execute import PlanAndExecute, load_agent_executor, load_chat_planner\n",
    "from langchain.llms import OpenAI\n",
    "from langchain import SerpAPIWrapper\n",
    "from langchain.agents.tools import Tool\n",
    "from langchain import LLMMathChain"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "0b10d200",
   "metadata": {},
   "source": [
    "## Tools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3c00f724",
   "metadata": {},
   "outputs": [],
   "source": [
    "search = SerpAPIWrapper()\n",
    "llm = OpenAI(temperature=0)\n",
    "llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)\n",
    "tools = [\n",
    "    Tool(\n",
    "        name = \"Search\",\n",
    "        func=search.run,\n",
    "        description=\"useful for when you need to answer questions about current events\"\n",
    "    ),\n",
    "    Tool(\n",
    "        name=\"Calculator\",\n",
    "        func=llm_math_chain.run,\n",
    "        description=\"useful for when you need to answer questions about math\"\n",
    "    ),\n",
    "]"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "ce38ae84",
   "metadata": {},
   "source": [
    "## Planner, Executor, and Agent"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0ab2cadd",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = ChatOpenAI(temperature=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7b2419f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "planner = load_chat_planner(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ed9f518b",
   "metadata": {},
   "outputs": [],
   "source": [
    "executor = load_agent_executor(model, tools, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "36943178",
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = PlanAndExecute(planner=planner, executor=executor, verbose=True)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "8be9f1bd",
   "metadata": {},
   "source": [
    "## Run Example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4891062e",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new PlanAndExecute chain...\u001b[0m\n",
      "steps=[Step(value=\"Search for Leo DiCaprio's girlfriend on the internet.\"), Step(value='Find her current age.'), Step(value='Raise her current age to the 0.43 power using a calculator or programming language.'), Step(value='Output the result.'), Step(value=\"Given the above steps taken, respond to the user's original question.\\n\\n\")]\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"Who is Leo DiCaprio's girlfriend?\"\n",
      "}\n",
      "``` \n",
      "\n",
      "\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mDiCaprio broke up with girlfriend Camila Morrone, 25, in the summer of 2022, after dating for four years. He's since been linked to another famous supermodel – Gigi Hadid. The power couple were first supposedly an item in September after being spotted getting cozy during a party at New York Fashion Week.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mBased on the previous observation, I can provide the answer to the current objective. \n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Final Answer\",\n",
      "  \"action_input\": \"Leo DiCaprio is currently linked to Gigi Hadid.\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "*****\n",
      "\n",
      "Step: Search for Leo DiCaprio's girlfriend on the internet.\n",
      "\n",
      "Response: Leo DiCaprio is currently linked to Gigi Hadid.\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"What is Gigi Hadid's current age?\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mPrevious steps: steps=[(Step(value=\"Search for Leo DiCaprio's girlfriend on the internet.\"), StepResponse(response='Leo DiCaprio is currently linked to Gigi Hadid.'))]\n",
      "\n",
      "Current objective: value='Find her current age.'\n",
      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"What is Gigi Hadid's current age?\"\n",
      "}\n",
      "```\n",
      "\n",
      "\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mPrevious steps: steps=[(Step(value=\"Search for Leo DiCaprio's girlfriend on the internet.\"), StepResponse(response='Leo DiCaprio is currently linked to Gigi Hadid.')), (Step(value='Find her current age.'), StepResponse(response='28 years'))]\n",
      "\n",
      "Current objective: None\n",
      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Final Answer\",\n",
      "  \"action_input\": \"Gigi Hadid's current age is 28 years.\"\n",
      "}\n",
      "```\n",
      "\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "*****\n",
      "\n",
      "Step: Find her current age.\n",
      "\n",
      "Response: Gigi Hadid's current age is 28 years.\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Calculator\",\n",
      "  \"action_input\": \"28 ** 0.43\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
      "28 ** 0.43\u001b[32;1m\u001b[1;3m\n",
      "```text\n",
      "28 ** 0.43\n",
      "```\n",
      "...numexpr.evaluate(\"28 ** 0.43\")...\n",
      "\u001b[0m\n",
      "Answer: \u001b[33;1m\u001b[1;3m4.1906168361987195\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.1906168361987195\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mThe next step is to provide the answer to the user's question.\n",
      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Final Answer\",\n",
      "  \"action_input\": \"Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\"\n",
      "}\n",
      "```\n",
      "\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "*****\n",
      "\n",
      "Step: Raise her current age to the 0.43 power using a calculator or programming language.\n",
      "\n",
      "Response: Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Final Answer\",\n",
      "  \"action_input\": \"The result is approximately 4.19.\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "*****\n",
      "\n",
      "Step: Output the result.\n",
      "\n",
      "Response: The result is approximately 4.19.\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Final Answer\",\n",
      "  \"action_input\": \"Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "*****\n",
      "\n",
      "Step: Given the above steps taken, respond to the user's original question.\n",
      "\n",
      "\n",
      "\n",
      "Response: Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\""
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aa3ec998",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": 5
}