langchain/docs/examples/agents/custom_tools.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5436020b",
   "metadata": {},
   "source": [
    "# Defining Custom Tools\n",
    "\n",
    "When constructing your own agent, you will need to provide it with a list of Tools that it can use. A Tool is defined as below.\n",
    "\n",
    "```python\n",
    "class Tool(NamedTuple):\n",
    "    \"\"\"Interface for tools.\"\"\"\n",
    "\n",
    "    name: str\n",
    "    func: Callable[[str], str]\n",
    "    description: Optional[str] = None\n",
    "```\n",
    "\n",
    "The two required components of a Tool are the name and then the tool itself. A tool description is optional, as it is needed for some agents but not all."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1aaba18c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import things that are needed generically\n",
    "from langchain.agents import initialize_agent, Tool\n",
    "from langchain.llms import OpenAI\n",
    "from langchain import LLMMathChain, SerpAPIWrapper"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e2c3874",
   "metadata": {},
   "source": [
    "Initialize the LLM to use for the agent."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "36ed392e",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f8bc72c2",
   "metadata": {},
   "source": [
    "## Completely New Tools\n",
    "First, we show how to create completely new tools from scratch."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "56ff7670",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the tool configs that are needed.\n",
    "search = SerpAPIWrapper()\n",
    "llm_math_chain = LLMMathChain(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",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "5b93047d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Construct the agent. We will use the default agent type here.\n",
    "# See documentation for a full list of options.\n",
    "llm = OpenAI(temperature=0)\n",
    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6f96a891",
   "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 find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
      "Action: Search\n",
      "Action Input: Olivia Wilde's boyfriend\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mHarry Styles\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate Harry Styles' age raised to the 0.23 power.\n",
      "Action: Calculator\n",
      "Action Input: 23^0.23\u001b[0m\n",
      "\n",
      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
      "23^0.23\u001b[32;1m\u001b[1;3m\n",
      "\n",
      "```python\n",
      "import math\n",
      "print(math.pow(23, 0.23))\n",
      "```\n",
      "\u001b[0m\n",
      "Answer: \u001b[33;1m\u001b[1;3m2.0568252837687546\n",
      "\u001b[0m\n",
      "\u001b[1m> Finished LLMMathChain chain.\u001b[0m\n",
      "\n",
      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.0568252837687546\n",
      "\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
      "Final Answer: Harry Styles' age raised to the 0.23 power is 2.0568252837687546.\u001b[0m\n",
      "\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"Harry Styles' age raised to the 0.23 power is 2.0568252837687546.\""
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d0430d6",
   "metadata": {},
   "source": [
    "## Modify existing tools\n",
    "\n",
    "Now, we show how to load existing tools and just modify them. In the example below, we do something really simple and change the Search tool to have the name `Google Search`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "79213f40",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import load_tools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "e1067dcb",
   "metadata": {},
   "outputs": [],
   "source": [
    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "6c66ffe8",
   "metadata": {},
   "outputs": [],
   "source": [
    "tools[0].name = \"Google Search\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "f45b5bc3",
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "565e2b9b",
   "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 find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
      "Action: Google Search\n",
      "Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mHarry Styles\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Harry Styles' age\n",
      "Action: Google Search\n",
      "Action Input: \"Harry Styles age\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 raised to the 0.23 power\n",
      "Action: Calculator\n",
      "Action Input: 28^0.23\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
      "\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: Harry Styles is Olivia Wilde's boyfriend and his current age raised to the 0.23 power is 2.1520202182226886.\u001b[0m\n",
      "\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"Harry Styles is Olivia Wilde's boyfriend and his current age raised to the 0.23 power is 2.1520202182226886.\""
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3450512e",
   "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": "3.10.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}