mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-13 02:57:22 +00:00
141 lines
3.7 KiB
Plaintext
141 lines
3.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "raw",
|
|
"id": "b8782af6-f49e-40da-9f7a-4765113b17ed",
|
|
"metadata": {},
|
|
"source": [
|
|
"---\n",
|
|
"sidebar_class_name: hidden\n",
|
|
"---"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "5125a1e3",
|
|
"metadata": {},
|
|
"source": [
|
|
"# [Deprecated] Experimental Anthropic Tools Wrapper\n",
|
|
"\n",
|
|
":::warning\n",
|
|
"\n",
|
|
"The Anthropic API officially supports tool-calling so this workaround is no longer needed. Please use [ChatAnthropic](/docs/integrations/chat/anthropic) with `langchain-anthropic>=0.1.15`.\n",
|
|
"\n",
|
|
":::\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 pydantic 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/how_to/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": ".venv",
|
|
"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
|
|
}
|