langchain/docs/modules/chat/examples/agent.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e58f4d5a",
   "metadata": {},
   "source": [
    "# Agent\n",
    "This notebook covers how to create a custom agent for a chat model. It will utilize chat specific prompts."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5268c7fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
    "from langchain.chains import LLMChain\n",
    "from langchain.utilities import SerpAPIWrapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "fbaa4dbe",
   "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",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f3ba6f08",
   "metadata": {},
   "outputs": [],
   "source": [
    "prefix = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\"\"\"\n",
    "suffix = \"\"\"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\"\"\n",
    "\n",
    "prompt = ZeroShotAgent.create_prompt(\n",
    "    tools, \n",
    "    prefix=prefix, \n",
    "    suffix=suffix, \n",
    "    input_variables=[]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3547a37d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.prompts.chat import (\n",
    "    ChatPromptTemplate,\n",
    "    SystemMessagePromptTemplate,\n",
    "    AIMessagePromptTemplate,\n",
    "    HumanMessagePromptTemplate,\n",
    ")\n",
    "from langchain.schema import (\n",
    "    AIMessage,\n",
    "    HumanMessage,\n",
    "    SystemMessage\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a78f886f",
   "metadata": {},
   "outputs": [],
   "source": [
    "messages = [\n",
    "    SystemMessagePromptTemplate(prompt=prompt),\n",
    "    HumanMessagePromptTemplate.from_template(\"{input}\\n\\nThis was your previous work \"\n",
    "                f\"(but I haven't seen any of it! I only see what \"\n",
    "                \"you return as final answer):\\n{agent_scratchpad}\")\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "dadadd70",
   "metadata": {},
   "outputs": [],
   "source": [
    "prompt = ChatPromptTemplate.from_messages(messages)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "b7180182",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm_chain = LLMChain(llm=ChatOpenAI(temperature=0), prompt=prompt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ddddb07b",
   "metadata": {},
   "outputs": [],
   "source": [
    "tool_names = [tool.name for tool in tools]\n",
    "agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "36aef054",
   "metadata": {},
   "outputs": [],
   "source": [
    "agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "33a4d6cc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mArrr, ye be in luck, matey! I'll find ye the answer to yer question.\n",
      "\n",
      "Thought: I need to search for the current population of Canada.\n",
      "Action: Search\n",
      "Action Input: \"current population of Canada 2023\"\n",
      "\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,623,091 as of Saturday, March 4, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mAhoy, me hearties! I've found the answer to yer question.\n",
      "\n",
      "Final Answer: As of March 4, 2023, the population of Canada be 38,623,091. Arrr!\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'As of March 4, 2023, the population of Canada be 38,623,091. Arrr!'"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.run(\"How many people live in canada as of 2023?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6aefe978",
   "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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}