{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import Tool, AgentExecutor, BaseMultiActionAgent\n",
    "from langchain import OpenAI, SerpAPIWrapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def random_word(query: str) -> str:\n",
    "    print(\"\\nNow I'm doing this!\")\n",
    "    return f\"{query}, foo\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "search = SerpAPIWrapper()\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 = \"RandomWord\",\n",
    "        func=random_word,\n",
    "        description=\"call this to get a random word.\",\n",
    "    )\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.tools import tool\n",
    "\n",
    "@tool\n",
    "def tool1(event) -> str:\n",
    "    \"\"\"这里必须添加描述，不然AssertionError: Function must have a docstring if description not provided.\"\"\"\n",
    "    return \"111\"\n",
    "\n",
    "from langchain.tools import tool\n",
    "\n",
    "@tool\n",
    "def tool2(event) -> str:\n",
    "    \"\"\"这里必须添加描述，不然AssertionError: Function must have a docstring if description not provided.\"\"\"\n",
    "    return \"222\"\n",
    "\n",
    "tools = [tool1, tool2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from typing import List, Tuple, Any, Union\n",
    "from langchain.schema import AgentAction, AgentFinish\n",
    "\n",
    "class FakeAgent(BaseMultiActionAgent):\n",
    "    \"\"\"Fake Custom Agent.\"\"\"\n",
    "    \n",
    "    @property\n",
    "    def input_keys(self):\n",
    "        return [\"input\"]\n",
    "    \n",
    "    def plan(\n",
    "        self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
    "    ) -> Union[List[AgentAction], AgentFinish]:\n",
    "        \"\"\"Given input, decided what to do.\n",
    "\n",
    "        Args:\n",
    "            intermediate_steps: Steps the LLM has taken to date,\n",
    "                along with observations\n",
    "            **kwargs: User inputs.\n",
    "\n",
    "        Returns:\n",
    "            Action specifying what tool to use.\n",
    "        \"\"\"\n",
    "        print(\"lizhen0\",intermediate_steps)\n",
    "        if len(intermediate_steps) == 0:\n",
    "            print(\"lizhen1\",intermediate_steps)\n",
    "            return [\n",
    "                AgentAction(tool=\"tool1\", tool_input=kwargs[\"input\"], log=\"\"),\n",
    "                AgentAction(tool=\"tool2\", tool_input=kwargs[\"input\"], log=\"\"),\n",
    "            ]\n",
    "        else:\n",
    "            for tuple in intermediate_steps:\n",
    "                print(tuple[0].tool, tuple[1])\n",
    "            return AgentFinish(return_values={\"output\": \"bar\"}, log=\"\")\n",
    "\n",
    "    async def aplan(\n",
    "        self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
    "    ) -> Union[List[AgentAction], AgentFinish]:\n",
    "        \"\"\"Given input, decided what to do.\n",
    "\n",
    "        Args:\n",
    "            intermediate_steps: Steps the LLM has taken to date,\n",
    "                along with observations\n",
    "            **kwargs: User inputs.\n",
    "\n",
    "        Returns:\n",
    "            Action specifying what tool to use.\n",
    "        \"\"\"\n",
    "        if len(intermediate_steps) == 0:\n",
    "            return [\n",
    "                AgentAction(tool=\"tool1\", tool_input=kwargs[\"input\"], log=\"\"),\n",
    "                AgentAction(tool=\"tool2\", tool_input=kwargs[\"input\"], log=\"\"),\n",
    "            ]\n",
    "        else:\n",
    "            return AgentFinish(return_values={\"output\": \"bar\"}, log=\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = FakeAgent()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "lizhen0 []\n",
      "lizhen1 []\n",
      "\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[36;1m\u001b[1;3m111\u001b[0m\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[33;1m\u001b[1;3m222\u001b[0mlizhen0 [(AgentAction(tool='tool1', tool_input='How many people live in canada as of 2023?', log=''), '111'), (AgentAction(tool='tool2', tool_input='How many people live in canada as of 2023?', log=''), '222')]\n",
      "tool1 111\n",
      "tool2 222\n",
      "\u001b[32;1m\u001b[1;3m\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'bar'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.run(\"How many people live in canada as of 2023?\")"
   ]
  }
 ],
 "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
}