{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import load_tools\n",
    "from langchain.agents import initialize_agent\n",
    "from langchain.agents import AgentType\n",
    "from langchain.llms import OpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0, model_name='text-davinci-002')\n",
    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, return_intermediate_steps=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m I need to know who the current CEO of TikTok is, and then I need to do some math.\n",
      "Action: Search\n",
      "Action Input: \"TikTok CEO\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mShou Chew\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to know how old Shou Chew is.\n",
      "Action: Search\n",
      "Action Input: \"Shou Chew age\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m40 years\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to do some math.\n",
      "Action: Calculator\n",
      "Action Input: 40+10\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 50\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: The current CEO of TikTok is Shou Chew, and he is 50 years old.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "response = agent({\"input\":\"抖音现任的CEO是谁？他年龄加10岁等于多少？\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[\n",
      "  [\n",
      "    [\n",
      "      \"Search\",\n",
      "      \"TikTok CEO\",\n",
      "      \" I need to know who the current CEO of TikTok is, and then I need to do some math.\\nAction: Search\\nAction Input: \\\"TikTok CEO\\\"\"\n",
      "    ],\n",
      "    \"Shou Chew\"\n",
      "  ],\n",
      "  [\n",
      "    [\n",
      "      \"Search\",\n",
      "      \"Shou Chew age\",\n",
      "      \" I need to know how old Shou Chew is.\\nAction: Search\\nAction Input: \\\"Shou Chew age\\\"\"\n",
      "    ],\n",
      "    \"40 years\"\n",
      "  ],\n",
      "  [\n",
      "    [\n",
      "      \"Calculator\",\n",
      "      \"40+10\",\n",
      "      \" I need to do some math.\\nAction: Calculator\\nAction Input: 40+10\"\n",
      "    ],\n",
      "    \"Answer: 50\"\n",
      "  ]\n",
      "]\n"
     ]
    }
   ],
   "source": [
    "# The actual return type is a NamedTuple for the agent action, and then an observation\n",
    "# print(response[\"intermediate_steps\"])\n",
    "\n",
    "import json\n",
    "print(json.dumps(response[\"intermediate_steps\"], indent=2))"
   ]
  }
 ],
 "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": "3.10.10"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}