{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import Tool, AgentExecutor, BaseSingleActionAgent\n",
    "from langchain import OpenAI, SerpAPIWrapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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",
    "        return_direct=True\n",
    "    )\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from typing import List, Tuple, Any, Union\n",
    "from langchain.schema import AgentAction, AgentFinish\n",
    "\n",
    "class FakeAgent(BaseSingleActionAgent):\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[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",
    "        return AgentAction(tool=\"Search\", tool_input=kwargs[\"input\"], log=\"\")\n",
    "\n",
    "    async def aplan(\n",
    "        self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
    "    ) -> Union[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",
    "        return AgentAction(tool=\"Search\", tool_input=kwargs[\"input\"], log=\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = FakeAgent()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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\u001b[0m\u001b[36;1m\u001b[1;3mThe current population of Canada is 38,680,894 as of Sunday, May 7, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The current population of Canada is 38,680,894 as of Sunday, May 7, 2023, based on Worldometer elaboration of the latest United Nations data.'"
      ]
     },
     "execution_count": 6,
     "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
}