This notebook shows how to use an experimental wrapper around Anthropic that gives it tool calling and structured output capabilities. It follows Anthropic's guidehere

The wrapper is available from thelangchain-anthropic package, and it also requires the optional dependencydefusedxml for parsing XML output from the llm.

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.

%pip install-qU langchain-anthropic defusedxml
from langchain_anthropic.experimentalimport ChatAnthropicTools

Tool Binding​

ChatAnthropicTools exposes abind_tools method that allows you to pass in Pydantic models or BaseTools to the llm.

from pydanticimport BaseModel


classPerson(BaseModel):
    name:str
    age:int


model= ChatAnthropicTools(model="claude-3-opus-20240229").bind_tools(tools=[Person])
model.invoke("I am a 27 year old named Erick")

AIMessage(content='', additional_kwargs={'tool_calls': [{'function': {'name': 'Person', 'arguments': '{"name": "Erick", "age": "27"}'}, 'type': 'function'}]})

Structured Output​

ChatAnthropicTools also implements thewith_structured_output spec for extracting values. Note: this may not be as stable as with models that explicitly offer tool calling.

chain= ChatAnthropicTools(model="claude-3-opus-20240229").with_structured_output(
    Person
)
chain.invoke("I am a 27 year old named Erick")

Person(name='Erick', age=27)

Related​

• Chat modelconceptual guide
• Chat modelhow-to guides