langchain/docs/docs/integrations/chat/anthropic_functions.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5125a1e3",
   "metadata": {},
   "source": [
    "# Anthropic Tools\n",
    "\n",
    "This notebook shows how to use an experimental wrapper around Anthropic that gives it tool calling and structured output capabilities. It follows Anthropic's guide [here](https://docs.anthropic.com/claude/docs/functions-external-tools)\n",
    "\n",
    "The wrapper is available from the `langchain-anthropic` package, and it also requires the optional dependency `defusedxml` for parsing XML output from the llm.\n",
    "\n",
    "Note: this is a beta feature that will be replaced by Anthropic's formal implementation of tool calling, but it is useful for testing and experimentation in the meantime."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "378be79b",
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install -qU langchain-anthropic defusedxml\n",
    "from langchain_anthropic.experimental import ChatAnthropicTools"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "65499965",
   "metadata": {},
   "source": [
    "## Tool Binding\n",
    "\n",
    "`ChatAnthropicTools` exposes a `bind_tools` method that allows you to pass in Pydantic models or BaseTools to the llm."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e1d535f6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content='', additional_kwargs={'tool_calls': [{'function': {'name': 'Person', 'arguments': '{\"name\": \"Erick\", \"age\": \"27\"}'}, 'type': 'function'}]})"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain_core.pydantic_v1 import BaseModel\n",
    "\n",
    "\n",
    "class Person(BaseModel):\n",
    "    name: str\n",
    "    age: int\n",
    "\n",
    "\n",
    "model = ChatAnthropicTools(model=\"claude-3-opus-20240229\").bind_tools(tools=[Person])\n",
    "model.invoke(\"I am a 27 year old named Erick\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fcc9eaf4",
   "metadata": {},
   "source": [
    "## Structured Output\n",
    "\n",
    "`ChatAnthropicTools` also implements the [`with_structured_output` spec](/docs/modules/model_io/chat/structured_output) for extracting values. Note: this may not be as stable as with models that explicitly offer tool calling."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "0779c320",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Person(name='Erick', age=27)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain = ChatAnthropicTools(model=\"claude-3-opus-20240229\").with_structured_output(\n",
    "    Person\n",
    ")\n",
    "chain.invoke(\"I am a 27 year old named Erick\")"
   ]
  }
 ],
 "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}