langchain_anthropic.chat_models.ChatAnthropic

Note

ChatAnthropic implements the standard Runnable Interface. 🏃

The Runnable Interface has additional methods that are available on runnables, such as with_types, with_retry, assign, bind, get_graph, and more.

class langchain_anthropic.chat_models.ChatAnthropic[source]

Bases: BaseChatModel

Anthropic chat models.

See https://docs.anthropic.com/en/docs/models-overview for a list of the latest models.

Setup:

Install langchain-anthropic and set environment variable ANTHROPIC_API_KEY.

pip install -U langchain-anthropic
export ANTHROPIC_API_KEY="your-api-key"
Key init args — completion params:
model: str

Name of Anthropic model to use. E.g. “claude-3-sonnet-20240229”.

temperature: float

Sampling temperature. Ranges from 0.0 to 1.0.

max_tokens: Optional[int]

Max number of tokens to generate.

Key init args — client params:
timeout: Optional[float]

Timeout for requests.

max_retries: int

Max number of retries if a request fails.

api_key: Optional[str]

Anthropic API key. If not passed in will be read from env var ANTHROPIC_API_KEY.

base_url: Optional[str]

Base URL for API requests. Only specify if using a proxy or service emulator.

See full list of supported init args and their descriptions in the params section.

Instantiate:
from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(
    model="claude-3-sonnet-20240229",
    temperature=0,
    max_tokens=1024,
    timeout=None,
    max_retries=2,
    # api_key="...",
    # base_url="...",
    # other params...
)

NOTE: Any param which is not explicitly supported will be passed directly to the anthropic.Anthropic.messages.create(...) API every time to the model is invoked. For example:

from langchain_anthropic import ChatAnthropic
import anthropic

ChatAnthropic(..., extra_headers={}).invoke(...)

# results in underlying API call of:

anthropic.Anthropic(..).messages.create(..., extra_headers={})

# which is also equivalent to:

ChatAnthropic(...).invoke(..., extra_headers={})
Invoke:
messages = [
    ("system", "You are a helpful translator. Translate the user sentence to French."),
    ("human", "I love programming."),
]
llm.invoke(messages)
AIMessage(content="J'aime la programmation.", response_metadata={'id': 'msg_01Trik66aiQ9Z1higrD5XFx3', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 25, 'output_tokens': 11}}, id='run-5886ac5f-3c2e-49f5-8a44-b1e92808c929-0', usage_metadata={'input_tokens': 25, 'output_tokens': 11, 'total_tokens': 36})
Stream:
for chunk in llm.stream(messages):
    print(chunk)
AIMessageChunk(content='J', id='run-272ff5f9-8485-402c-b90d-eac8babc5b25')
AIMessageChunk(content="'", id='run-272ff5f9-8485-402c-b90d-eac8babc5b25')
AIMessageChunk(content='a', id='run-272ff5f9-8485-402c-b90d-eac8babc5b25')
AIMessageChunk(content='ime', id='run-272ff5f9-8485-402c-b90d-eac8babc5b25')
AIMessageChunk(content=' la', id='run-272ff5f9-8485-402c-b90d-eac8babc5b25')
AIMessageChunk(content=' programm', id='run-272ff5f9-8485-402c-b90d-eac8babc5b25')
AIMessageChunk(content='ation', id='run-272ff5f9-8485-402c-b90d-eac8babc5b25')
AIMessageChunk(content='.', id='run-272ff5f9-8485-402c-b90d-eac8babc5b25')
stream = llm.stream(messages)
full = next(stream)
for chunk in stream:
    full += chunk
full
AIMessageChunk(content="J'aime la programmation.", id='run-b34faef0-882f-4869-a19c-ed2b856e6361')
Async:
await llm.ainvoke(messages)

# stream:
# async for chunk in (await llm.astream(messages))

# batch:
# await llm.abatch([messages])
AIMessage(content="J'aime la programmation.", response_metadata={'id': 'msg_01Trik66aiQ9Z1higrD5XFx3', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 25, 'output_tokens': 11}}, id='run-5886ac5f-3c2e-49f5-8a44-b1e92808c929-0', usage_metadata={'input_tokens': 25, 'output_tokens': 11, 'total_tokens': 36})
Tool calling:
from langchain_core.pydantic_v1 import BaseModel, Field

class GetWeather(BaseModel):
    '''Get the current weather in a given location'''

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")

class GetPopulation(BaseModel):
    '''Get the current population in a given location'''

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")

llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])
ai_msg = llm_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")
ai_msg.tool_calls
[{'name': 'GetWeather',
  'args': {'location': 'Los Angeles, CA'},
  'id': 'toolu_01KzpPEAgzura7hpBqwHbWdo'},
 {'name': 'GetWeather',
  'args': {'location': 'New York, NY'},
  'id': 'toolu_01JtgbVGVJbiSwtZk3Uycezx'},
 {'name': 'GetPopulation',
  'args': {'location': 'Los Angeles, CA'},
  'id': 'toolu_01429aygngesudV9nTbCKGuw'},
 {'name': 'GetPopulation',
  'args': {'location': 'New York, NY'},
  'id': 'toolu_01JPktyd44tVMeBcPPnFSEJG'}]

See ChatAnthropic.bind_tools() method for more.

Structured output:
from typing import Optional

from langchain_core.pydantic_v1 import BaseModel, Field

class Joke(BaseModel):
    '''Joke to tell user.'''

    setup: str = Field(description="The setup of the joke")
    punchline: str = Field(description="The punchline to the joke")
    rating: Optional[int] = Field(description="How funny the joke is, from 1 to 10")

structured_llm = llm.with_structured_output(Joke)
structured_llm.invoke("Tell me a joke about cats")
Joke(setup='Why was the cat sitting on the computer?', punchline='To keep an eye on the mouse!', rating=None)

See ChatAnthropic.with_structured_output() for more.

Image input:
import base64
import httpx
from langchain_core.messages import HumanMessage

image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
image_data = base64.b64encode(httpx.get(image_url).content).decode("utf-8")
message = HumanMessage(
    content=[
        {"type": "text", "text": "describe the weather in this image"},
        {
            "type": "image_url",
            "image_url": {"url": f"data:image/jpeg;base64,{image_data}"},
        },
    ],
)
ai_msg = llm.invoke([message])
ai_msg.content
"The image depicts a sunny day with a partly cloudy sky. The sky is a brilliant blue color with scattered white clouds drifting across. The lighting and cloud patterns suggest pleasant, mild weather conditions. The scene shows a grassy field or meadow with a wooden boardwalk trail leading through it, indicating an outdoor setting on a nice day well-suited for enjoying nature."
Token usage:
ai_msg = llm.invoke(messages)
ai_msg.usage_metadata
{'input_tokens': 25, 'output_tokens': 11, 'total_tokens': 36}

Message chunks containing token usage will be included during streaming by default:

stream = llm.stream(messages)
full = next(stream)
for chunk in stream:
    full += chunk
full.usage_metadata
{'input_tokens': 25, 'output_tokens': 11, 'total_tokens': 36}

These can be disabled by setting stream_usage=False in the stream method, or by setting stream_usage=False when initializing ChatAnthropic.

Response metadata
ai_msg = llm.invoke(messages)
ai_msg.response_metadata
{'id': 'msg_013xU6FHEGEq76aP4RgFerVT',
 'model': 'claude-3-sonnet-20240229',
 'stop_reason': 'end_turn',
 'stop_sequence': None,
 'usage': {'input_tokens': 25, 'output_tokens': 11}}
param anthropic_api_key: SecretStr [Optional] (alias 'api_key')

Automatically read from env var ANTHROPIC_API_KEY if not provided.

Constraints
  • type = string

  • writeOnly = True

  • format = password

param anthropic_api_url: Optional[str] [Optional] (alias 'base_url')

Base URL for API requests. Only specify if using a proxy or service emulator.

If a value isn’t passed in, will attempt to read the value first from ANTHROPIC_API_URL and if that is not set, ANTHROPIC_BASE_URL. If neither are set, the default value of ‘https://api.anthropic.com’ will be used.

param cache: Union[BaseCache, bool, None] = None

Whether to cache the response.

  • If true, will use the global cache.

  • If false, will not use a cache

  • If None, will use the global cache if it’s set, otherwise no cache.

  • If instance of BaseCache, will use the provided cache.

Caching is not currently supported for streaming methods of models.

param callback_manager: Optional[BaseCallbackManager] = None

Deprecated since version 0.1.7: Use callbacks instead.

Callback manager to add to the run trace.

param callbacks: Callbacks = None

Callbacks to add to the run trace.

param custom_get_token_ids: Optional[Callable[[str], List[int]]] = None

Optional encoder to use for counting tokens.

param default_headers: Optional[Mapping[str, str]] = None

Headers to pass to the Anthropic clients, will be used for every API call.

param default_request_timeout: Optional[float] = None (alias 'timeout')

Timeout for requests to Anthropic Completion API.

param disable_streaming: Union[bool, Literal['tool_calling']] = False

Whether to disable streaming for this model.

If streaming is bypassed, then stream()/astream() will defer to invoke()/ainvoke().

  • If True, will always bypass streaming case.

  • If “tool_calling”, will bypass streaming case only when the model is called with a tools keyword argument.

  • If False (default), will always use streaming case if available.

param max_retries: int = 2

Number of retries allowed for requests sent to the Anthropic Completion API.

param max_tokens: int = 1024 (alias 'max_tokens_to_sample')

Denotes the number of tokens to predict per generation.

param metadata: Optional[Dict[str, Any]] = None

Metadata to add to the run trace.

param model: str [Required] (alias 'model_name')

Model name to use.

param model_kwargs: Dict[str, Any] [Optional]
param rate_limiter: Optional[BaseRateLimiter] = None

An optional rate limiter to use for limiting the number of requests.

param stop_sequences: Optional[List[str]] = None (alias 'stop')

Default stop sequences.

param stream_usage: bool = True

Whether to include usage metadata in streaming output. If True, additional message chunks will be generated during the stream including usage metadata.

param streaming: bool = False

Whether to use streaming or not.

param tags: Optional[List[str]] = None

Tags to add to the run trace.

param temperature: Optional[float] = None

A non-negative float that tunes the degree of randomness in generation.

param top_k: Optional[int] = None

Number of most likely tokens to consider at each step.

param top_p: Optional[float] = None

Total probability mass of tokens to consider at each step.

param verbose: bool [Optional]

Whether to print out response text.

__call__(messages: List[BaseMessage], stop: Optional[List[str]] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) BaseMessage

Deprecated since version langchain-core==0.1.7: Use invoke instead.

Parameters
Return type

BaseMessage

async abatch(inputs: List[Input], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Optional[Any]) List[Output]

Default implementation runs ainvoke in parallel using asyncio.gather.

The default implementation of batch works well for IO bound runnables.

Subclasses should override this method if they can batch more efficiently; e.g., if the underlying Runnable uses an API which supports a batch mode.

Parameters
  • inputs (List[Input]) – A list of inputs to the Runnable.

  • config (Optional[Union[RunnableConfig, List[RunnableConfig]]]) – A config to use when invoking the Runnable. The config supports standard keys like ‘tags’, ‘metadata’ for tracing purposes, ‘max_concurrency’ for controlling how much work to do in parallel, and other keys. Please refer to the RunnableConfig for more details. Defaults to None.

  • return_exceptions (bool) – Whether to return exceptions instead of raising them. Defaults to False.

  • kwargs (Optional[Any]) – Additional keyword arguments to pass to the Runnable.

Returns

A list of outputs from the Runnable.

Return type

List[Output]

async abatch_as_completed(inputs: Sequence[Input], config: Optional[Union[RunnableConfig, Sequence[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Optional[Any]) AsyncIterator[Tuple[int, Union[Output, Exception]]]

Run ainvoke in parallel on a list of inputs, yielding results as they complete.

Parameters
  • inputs (Sequence[Input]) – A list of inputs to the Runnable.

  • config (Optional[Union[RunnableConfig, Sequence[RunnableConfig]]]) – A config to use when invoking the Runnable. The config supports standard keys like ‘tags’, ‘metadata’ for tracing purposes, ‘max_concurrency’ for controlling how much work to do in parallel, and other keys. Please refer to the RunnableConfig for more details. Defaults to None. Defaults to None.

  • return_exceptions (bool) – Whether to return exceptions instead of raising them. Defaults to False.

  • kwargs (Optional[Any]) – Additional keyword arguments to pass to the Runnable.

Yields

A tuple of the index of the input and the output from the Runnable.

Return type

AsyncIterator[Tuple[int, Union[Output, Exception]]]

async agenerate(messages: List[List[BaseMessage]], stop: Optional[List[str]] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, *, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, run_name: Optional[str] = None, run_id: Optional[UUID] = None, **kwargs: Any) LLMResult

Asynchronously pass a sequence of prompts to a model and return generations.

This method should make use of batched calls for models that expose a batched API.

Use this method when you want to:
  1. take advantage of batched calls,

  2. need more output from the model than just the top generated value,

  3. are building chains that are agnostic to the underlying language model

    type (e.g., pure text completion models vs chat models).

Parameters
  • messages (List[List[BaseMessage]]) – List of list of messages.

  • stop (Optional[List[str]]) – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

  • callbacks (Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]) – Callbacks to pass through. Used for executing additional functionality, such as logging or streaming, throughout generation.

  • **kwargs (Any) – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

  • tags (Optional[List[str]]) –

  • metadata (Optional[Dict[str, Any]]) –

  • run_name (Optional[str]) –

  • run_id (Optional[UUID]) –

  • **kwargs

Returns

An LLMResult, which contains a list of candidate Generations for each input

prompt and additional model provider-specific output.

Return type

LLMResult

async agenerate_prompt(prompts: List[PromptValue], stop: Optional[List[str]] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) LLMResult

Asynchronously pass a sequence of prompts and return model generations.

This method should make use of batched calls for models that expose a batched API.

Use this method when you want to:
  1. take advantage of batched calls,

  2. need more output from the model than just the top generated value,

  3. are building chains that are agnostic to the underlying language model

    type (e.g., pure text completion models vs chat models).

Parameters
  • prompts (List[PromptValue]) – List of PromptValues. A PromptValue is an object that can be converted to match the format of any language model (string for pure text generation models and BaseMessages for chat models).

  • stop (Optional[List[str]]) – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

  • callbacks (Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]) – Callbacks to pass through. Used for executing additional functionality, such as logging or streaming, throughout generation.

  • **kwargs (Any) – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

An LLMResult, which contains a list of candidate Generations for each input

prompt and additional model provider-specific output.

Return type

LLMResult

async ainvoke(input: LanguageModelInput, config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) BaseMessage

Default implementation of ainvoke, calls invoke from a thread.

The default implementation allows usage of async code even if the Runnable did not implement a native async version of invoke.

Subclasses should override this method if they can run asynchronously.

Parameters
  • input (LanguageModelInput) –

  • config (Optional[RunnableConfig]) –

  • stop (Optional[List[str]]) –

  • kwargs (Any) –

Return type

BaseMessage

async apredict(text: str, *, stop: Optional[Sequence[str]] = None, **kwargs: Any) str

Deprecated since version langchain-core==0.1.7: Use ainvoke instead.

Parameters
  • text (str) –

  • stop (Optional[Sequence[str]]) –

  • kwargs (Any) –

Return type

str

async apredict_messages(messages: List[BaseMessage], *, stop: Optional[Sequence[str]] = None, **kwargs: Any) BaseMessage

Deprecated since version langchain-core==0.1.7: Use ainvoke instead.

Parameters
  • messages (List[BaseMessage]) –

  • stop (Optional[Sequence[str]]) –

  • kwargs (Any) –

Return type

BaseMessage

as_tool(args_schema: Optional[Type[BaseModel]] = None, *, name: Optional[str] = None, description: Optional[str] = None, arg_types: Optional[Dict[str, Type]] = None) BaseTool

Beta

This API is in beta and may change in the future.

Create a BaseTool from a Runnable.

as_tool will instantiate a BaseTool with a name, description, and args_schema from a Runnable. Where possible, schemas are inferred from runnable.get_input_schema. Alternatively (e.g., if the Runnable takes a dict as input and the specific dict keys are not typed), the schema can be specified directly with args_schema. You can also pass arg_types to just specify the required arguments and their types.

Parameters
  • args_schema (Optional[Type[BaseModel]]) – The schema for the tool. Defaults to None.

  • name (Optional[str]) – The name of the tool. Defaults to None.

  • description (Optional[str]) – The description of the tool. Defaults to None.

  • arg_types (Optional[Dict[str, Type]]) – A dictionary of argument names to types. Defaults to None.

Returns

A BaseTool instance.

Return type

BaseTool

Typed dict input:

from typing import List
from typing_extensions import TypedDict
from langchain_core.runnables import RunnableLambda

class Args(TypedDict):
    a: int
    b: List[int]

def f(x: Args) -> str:
    return str(x["a"] * max(x["b"]))

runnable = RunnableLambda(f)
as_tool = runnable.as_tool()
as_tool.invoke({"a": 3, "b": [1, 2]})

dict input, specifying schema via args_schema:

from typing import Any, Dict, List
from langchain_core.pydantic_v1 import BaseModel, Field
from langchain_core.runnables import RunnableLambda

def f(x: Dict[str, Any]) -> str:
    return str(x["a"] * max(x["b"]))

class FSchema(BaseModel):
    """Apply a function to an integer and list of integers."""

    a: int = Field(..., description="Integer")
    b: List[int] = Field(..., description="List of ints")

runnable = RunnableLambda(f)
as_tool = runnable.as_tool(FSchema)
as_tool.invoke({"a": 3, "b": [1, 2]})

dict input, specifying schema via arg_types:

from typing import Any, Dict, List
from langchain_core.runnables import RunnableLambda

def f(x: Dict[str, Any]) -> str:
    return str(x["a"] * max(x["b"]))

runnable = RunnableLambda(f)
as_tool = runnable.as_tool(arg_types={"a": int, "b": List[int]})
as_tool.invoke({"a": 3, "b": [1, 2]})

String input:

from langchain_core.runnables import RunnableLambda

def f(x: str) -> str:
    return x + "a"

def g(x: str) -> str:
    return x + "z"

runnable = RunnableLambda(f) | g
as_tool = runnable.as_tool()
as_tool.invoke("b")

New in version 0.2.14.

async astream(input: LanguageModelInput, config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) AsyncIterator[BaseMessageChunk]

Default implementation of astream, which calls ainvoke. Subclasses should override this method if they support streaming output.

Parameters
  • input (LanguageModelInput) – The input to the Runnable.

  • config (Optional[RunnableConfig]) – The config to use for the Runnable. Defaults to None.

  • kwargs (Any) – Additional keyword arguments to pass to the Runnable.

  • stop (Optional[List[str]]) –

Yields

The output of the Runnable.

Return type

AsyncIterator[BaseMessageChunk]

astream_events(input: Any, config: Optional[RunnableConfig] = None, *, version: Literal['v1', 'v2'], include_names: Optional[Sequence[str]] = None, include_types: Optional[Sequence[str]] = None, include_tags: Optional[Sequence[str]] = None, exclude_names: Optional[Sequence[str]] = None, exclude_types: Optional[Sequence[str]] = None, exclude_tags: Optional[Sequence[str]] = None, **kwargs: Any) AsyncIterator[Union[StandardStreamEvent, CustomStreamEvent]]

Beta

This API is in beta and may change in the future.

Generate a stream of events.

Use to create an iterator over StreamEvents that provide real-time information about the progress of the Runnable, including StreamEvents from intermediate results.

A StreamEvent is a dictionary with the following schema:

  • event: str - Event names are of the

    format: on_[runnable_type]_(start|stream|end).

  • name: str - The name of the Runnable that generated the event.

  • run_id: str - randomly generated ID associated with the given execution of

    the Runnable that emitted the event. A child Runnable that gets invoked as part of the execution of a parent Runnable is assigned its own unique ID.

  • parent_ids: List[str] - The IDs of the parent runnables that

    generated the event. The root Runnable will have an empty list. The order of the parent IDs is from the root to the immediate parent. Only available for v2 version of the API. The v1 version of the API will return an empty list.

  • tags: Optional[List[str]] - The tags of the Runnable that generated

    the event.

  • metadata: Optional[Dict[str, Any]] - The metadata of the Runnable

    that generated the event.

  • data: Dict[str, Any]

Below is a table that illustrates some evens that might be emitted by various chains. Metadata fields have been omitted from the table for brevity. Chain definitions have been included after the table.

ATTENTION This reference table is for the V2 version of the schema.

event

name

chunk

input

output

on_chat_model_start

[model name]

{“messages”: [[SystemMessage, HumanMessage]]}

on_chat_model_stream

[model name]

AIMessageChunk(content=”hello”)

on_chat_model_end

[model name]

{“messages”: [[SystemMessage, HumanMessage]]}

AIMessageChunk(content=”hello world”)

on_llm_start

[model name]

{‘input’: ‘hello’}

on_llm_stream

[model name]

‘Hello’

on_llm_end

[model name]

‘Hello human!’

on_chain_start

format_docs

on_chain_stream

format_docs

“hello world!, goodbye world!”

on_chain_end

format_docs

[Document(…)]

“hello world!, goodbye world!”

on_tool_start

some_tool

{“x”: 1, “y”: “2”}

on_tool_end

some_tool

{“x”: 1, “y”: “2”}

on_retriever_start

[retriever name]

{“query”: “hello”}

on_retriever_end

[retriever name]

{“query”: “hello”}

[Document(…), ..]

on_prompt_start

[template_name]

{“question”: “hello”}

on_prompt_end

[template_name]

{“question”: “hello”}

ChatPromptValue(messages: [SystemMessage, …])

In addition to the standard events, users can also dispatch custom events (see example below).

Custom events will be only be surfaced with in the v2 version of the API!

A custom event has following format:

Attribute

Type

Description

name

str

A user defined name for the event.

data

Any

The data associated with the event. This can be anything, though we suggest making it JSON serializable.

Here are declarations associated with the standard events shown above:

format_docs:

def format_docs(docs: List[Document]) -> str:
    '''Format the docs.'''
    return ", ".join([doc.page_content for doc in docs])

format_docs = RunnableLambda(format_docs)

some_tool:

@tool
def some_tool(x: int, y: str) -> dict:
    '''Some_tool.'''
    return {"x": x, "y": y}

prompt:

template = ChatPromptTemplate.from_messages(
    [("system", "You are Cat Agent 007"), ("human", "{question}")]
).with_config({"run_name": "my_template", "tags": ["my_template"]})

Example:

from langchain_core.runnables import RunnableLambda

async def reverse(s: str) -> str:
    return s[::-1]

chain = RunnableLambda(func=reverse)

events = [
    event async for event in chain.astream_events("hello", version="v2")
]

# will produce the following events (run_id, and parent_ids
# has been omitted for brevity):
[
    {
        "data": {"input": "hello"},
        "event": "on_chain_start",
        "metadata": {},
        "name": "reverse",
        "tags": [],
    },
    {
        "data": {"chunk": "olleh"},
        "event": "on_chain_stream",
        "metadata": {},
        "name": "reverse",
        "tags": [],
    },
    {
        "data": {"output": "olleh"},
        "event": "on_chain_end",
        "metadata": {},
        "name": "reverse",
        "tags": [],
    },
]

Example: Dispatch Custom Event

from langchain_core.callbacks.manager import (
    adispatch_custom_event,
)
from langchain_core.runnables import RunnableLambda, RunnableConfig
import asyncio


async def slow_thing(some_input: str, config: RunnableConfig) -> str:
    """Do something that takes a long time."""
    await asyncio.sleep(1) # Placeholder for some slow operation
    await adispatch_custom_event(
        "progress_event",
        {"message": "Finished step 1 of 3"},
        config=config # Must be included for python < 3.10
    )
    await asyncio.sleep(1) # Placeholder for some slow operation
    await adispatch_custom_event(
        "progress_event",
        {"message": "Finished step 2 of 3"},
        config=config # Must be included for python < 3.10
    )
    await asyncio.sleep(1) # Placeholder for some slow operation
    return "Done"

slow_thing = RunnableLambda(slow_thing)

async for event in slow_thing.astream_events("some_input", version="v2"):
    print(event)
Parameters
  • input (Any) – The input to the Runnable.

  • config (Optional[RunnableConfig]) – The config to use for the Runnable.

  • version (Literal['v1', 'v2']) – The version of the schema to use either v2 or v1. Users should use v2. v1 is for backwards compatibility and will be deprecated in 0.4.0. No default will be assigned until the API is stabilized. custom events will only be surfaced in v2.

  • include_names (Optional[Sequence[str]]) – Only include events from runnables with matching names.

  • include_types (Optional[Sequence[str]]) – Only include events from runnables with matching types.

  • include_tags (Optional[Sequence[str]]) – Only include events from runnables with matching tags.

  • exclude_names (Optional[Sequence[str]]) – Exclude events from runnables with matching names.

  • exclude_types (Optional[Sequence[str]]) – Exclude events from runnables with matching types.

  • exclude_tags (Optional[Sequence[str]]) – Exclude events from runnables with matching tags.

  • kwargs (Any) – Additional keyword arguments to pass to the Runnable. These will be passed to astream_log as this implementation of astream_events is built on top of astream_log.

Yields

An async stream of StreamEvents.

Raises

NotImplementedError – If the version is not v1 or v2.

Return type

AsyncIterator[Union[StandardStreamEvent, CustomStreamEvent]]

batch(inputs: List[Input], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Optional[Any]) List[Output]

Default implementation runs invoke in parallel using a thread pool executor.

The default implementation of batch works well for IO bound runnables.

Subclasses should override this method if they can batch more efficiently; e.g., if the underlying Runnable uses an API which supports a batch mode.

Parameters
  • inputs (List[Input]) –

  • config (Optional[Union[RunnableConfig, List[RunnableConfig]]]) –

  • return_exceptions (bool) –

  • kwargs (Optional[Any]) –

Return type

List[Output]

batch_as_completed(inputs: Sequence[Input], config: Optional[Union[RunnableConfig, Sequence[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Optional[Any]) Iterator[Tuple[int, Union[Output, Exception]]]

Run invoke in parallel on a list of inputs, yielding results as they complete.

Parameters
  • inputs (Sequence[Input]) –

  • config (Optional[Union[RunnableConfig, Sequence[RunnableConfig]]]) –

  • return_exceptions (bool) –

  • kwargs (Optional[Any]) –

Return type

Iterator[Tuple[int, Union[Output, Exception]]]

bind_tools(tools: Sequence[Union[Dict[str, Any], Type, Callable, BaseTool]], *, tool_choice: Optional[Union[Dict[str, str], Literal['any', 'auto'], str]] = None, **kwargs: Any) Runnable[Union[PromptValue, str, Sequence[Union[BaseMessage, List[str], Tuple[str, str], str, Dict[str, Any]]]], BaseMessage][source]

Bind tool-like objects to this chat model.

Args:
tools: A list of tool definitions to bind to this chat model.

Supports Anthropic format tool schemas and any tool definition handled by langchain_core.utils.function_calling.convert_to_openai_tool().

tool_choice: Which tool to require the model to call.
Options are:
  • name of the tool (str): calls corresponding tool;

  • "auto" or None: automatically selects a tool (including no tool);

  • "any": force at least one tool to be called;

  • or a dict of the form:

    {"type": "tool", "name": "tool_name"}, or {"type: "any"}, or {"type: "auto"};

kwargs: Any additional parameters are passed directly to

self.bind(**kwargs).

Example:
from langchain_anthropic import ChatAnthropic
from langchain_core.pydantic_v1 import BaseModel, Field

class GetWeather(BaseModel):
    '''Get the current weather in a given location'''

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")

class GetPrice(BaseModel):
    '''Get the price of a specific product.'''

    product: str = Field(..., description="The product to look up.")


llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
llm_with_tools = llm.bind_tools([GetWeather, GetPrice])
llm_with_tools.invoke("what is the weather like in San Francisco",)
# -> AIMessage(
#     content=[
#         {'text': '<thinking>

Based on the user’s question, the relevant function to call is GetWeather, which requires the “location” parameter.

The user has directly specified the location as “San Francisco”. Since San Francisco is a well known city, I can reasonably infer they mean San Francisco, CA without needing the state specified.

All the required parameters are provided, so I can proceed with the API call. </thinking>’, ‘type’: ‘text’},

# {‘text’: None, ‘type’: ‘tool_use’, ‘id’: ‘toolu_01SCgExKzQ7eqSkMHfygvYuu’, ‘name’: ‘GetWeather’, ‘input’: {‘location’: ‘San Francisco, CA’}} # ], # response_metadata={‘id’: ‘msg_01GM3zQtoFv8jGQMW7abLnhi’, ‘model’: ‘claude-3-opus-20240229’, ‘stop_reason’: ‘tool_use’, ‘stop_sequence’: None, ‘usage’: {‘input_tokens’: 487, ‘output_tokens’: 145}}, # id=’run-87b1331e-9251-4a68-acef-f0a018b639cc-0’ # )

Example — force tool call with tool_choice ‘any’:
from langchain_anthropic import ChatAnthropic
from langchain_core.pydantic_v1 import BaseModel, Field

class GetWeather(BaseModel):
    '''Get the current weather in a given location'''

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")

class GetPrice(BaseModel):
    '''Get the price of a specific product.'''

    product: str = Field(..., description="The product to look up.")


llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
llm_with_tools = llm.bind_tools([GetWeather, GetPrice], tool_choice="any")
llm_with_tools.invoke("what is the weather like in San Francisco",)
Example — force specific tool call with tool_choice ‘<name_of_tool>’:
from langchain_anthropic import ChatAnthropic
from langchain_core.pydantic_v1 import BaseModel, Field

class GetWeather(BaseModel):
    '''Get the current weather in a given location'''

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")

class GetPrice(BaseModel):
    '''Get the price of a specific product.'''

    product: str = Field(..., description="The product to look up.")


llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
llm_with_tools = llm.bind_tools([GetWeather, GetPrice], tool_choice="GetWeather")
llm_with_tools.invoke("what is the weather like in San Francisco",)
Example — cache specific tools:
from langchain_anthropic import ChatAnthropic, convert_to_anthropic_tool
from langchain_core.pydantic_v1 import BaseModel, Field

class GetWeather(BaseModel):
    '''Get the current weather in a given location'''

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")

class GetPrice(BaseModel):
    '''Get the price of a specific product.'''

    product: str = Field(..., description="The product to look up.")

# We'll convert our pydantic class to the anthropic tool format
# before passing to bind_tools so that we can set the 'cache_control'
# field on our tool.
cached_price_tool = convert_to_anthropic_tool(GetPrice)
# Currently the only supported "cache_control" value is
# {"type": "ephemeral"}.
cached_price_tool["cache_control"] = {"type": "ephemeral"}

# We need to pass in extra headers to enable use of the beta cache
# control API.
llm = ChatAnthropic(
    model="claude-3-opus-20240229",
    temperature=0,
    extra_headers={"anthropic-beta": "prompt-caching-2024-07-31"}
)
llm_with_tools = llm.bind_tools([GetWeather, cached_price_tool])
llm_with_tools.invoke("what is the weather like in San Francisco",)

This outputs: .. code-block:: pycon

AIMessage(content=[{‘text’: “Certainly! I can help you find out the current weather in San Francisco. To get this information, I’ll use the GetWeather function. Let me fetch that data for you right away.”, ‘type’: ‘text’}, {‘id’: ‘toolu_01TS5h8LNo7p5imcG7yRiaUM’, ‘input’: {‘location’: ‘San Francisco, CA’}, ‘name’: ‘GetWeather’, ‘type’: ‘tool_use’}], response_metadata={‘id’: ‘msg_01Xg7Wr5inFWgBxE5jH9rpRo’, ‘model’: ‘claude-3-5-sonnet-20240620’, ‘stop_reason’: ‘tool_use’, ‘stop_sequence’: None, ‘usage’: {‘input_tokens’: 171, ‘output_tokens’: 96, ‘cache_creation_input_tokens’: 1470, ‘cache_read_input_tokens’: 0}}, id=’run-b36a5b54-5d69-470e-a1b0-b932d00b089e-0’, tool_calls=[{‘name’: ‘GetWeather’, ‘args’: {‘location’: ‘San Francisco, CA’}, ‘id’: ‘toolu_01TS5h8LNo7p5imcG7yRiaUM’, ‘type’: ‘tool_call’}], usage_metadata={‘input_tokens’: 171, ‘output_tokens’: 96, ‘total_tokens’: 267})

If we invoke the tool again, we can see that the “usage” information in the AIMessage.response_metadata shows that we had a cache hit: .. code-block:: pycon

AIMessage(content=[{‘text’: ‘To get the current weather in San Francisco, I can use the GetWeather function. Let me check that for you.’, ‘type’: ‘text’}, {‘id’: ‘toolu_01HtVtY1qhMFdPprx42qU2eA’, ‘input’: {‘location’: ‘San Francisco, CA’}, ‘name’: ‘GetWeather’, ‘type’: ‘tool_use’}], response_metadata={‘id’: ‘msg_016RfWHrRvW6DAGCdwB6Ac64’, ‘model’: ‘claude-3-5-sonnet-20240620’, ‘stop_reason’: ‘tool_use’, ‘stop_sequence’: None, ‘usage’: {‘input_tokens’: 171, ‘output_tokens’: 82, ‘cache_creation_input_tokens’: 0, ‘cache_read_input_tokens’: 1470}}, id=’run-88b1f825-dcb7-4277-ac27-53df55d22001-0’, tool_calls=[{‘name’: ‘GetWeather’, ‘args’: {‘location’: ‘San Francisco, CA’}, ‘id’: ‘toolu_01HtVtY1qhMFdPprx42qU2eA’, ‘type’: ‘tool_call’}], usage_metadata={‘input_tokens’: 171, ‘output_tokens’: 82, ‘total_tokens’: 253})

Parameters
  • tools (Sequence[Union[Dict[str, Any], Type, Callable, BaseTool]]) –

  • tool_choice (Optional[Union[Dict[str, str], Literal['any', 'auto'], str]]) –

  • kwargs (Any) –

Return type

Runnable[Union[PromptValue, str, Sequence[Union[BaseMessage, List[str], Tuple[str, str], str, Dict[str, Any]]]], BaseMessage]

call_as_llm(message: str, stop: Optional[List[str]] = None, **kwargs: Any) str

Deprecated since version langchain-core==0.1.7: Use invoke instead.

Parameters
  • message (str) –

  • stop (Optional[List[str]]) –

  • kwargs (Any) –

Return type

str

configurable_alternatives(which: ConfigurableField, *, default_key: str = 'default', prefix_keys: bool = False, **kwargs: Union[Runnable[Input, Output], Callable[[], Runnable[Input, Output]]]) RunnableSerializable[Input, Output]

Configure alternatives for Runnables that can be set at runtime.

Parameters
  • which (ConfigurableField) – The ConfigurableField instance that will be used to select the alternative.

  • default_key (str) – The default key to use if no alternative is selected. Defaults to “default”.

  • prefix_keys (bool) – Whether to prefix the keys with the ConfigurableField id. Defaults to False.

  • **kwargs (Union[Runnable[Input, Output], Callable[[], Runnable[Input, Output]]]) – A dictionary of keys to Runnable instances or callables that return Runnable instances.

Returns

A new Runnable with the alternatives configured.

Return type

RunnableSerializable[Input, Output]

from langchain_anthropic import ChatAnthropic
from langchain_core.runnables.utils import ConfigurableField
from langchain_openai import ChatOpenAI

model = ChatAnthropic(
    model_name="claude-3-sonnet-20240229"
).configurable_alternatives(
    ConfigurableField(id="llm"),
    default_key="anthropic",
    openai=ChatOpenAI()
)

# uses the default model ChatAnthropic
print(model.invoke("which organization created you?").content)

# uses ChatOpenAI
print(
    model.with_config(
        configurable={"llm": "openai"}
    ).invoke("which organization created you?").content
)
configurable_fields(**kwargs: Union[ConfigurableField, ConfigurableFieldSingleOption, ConfigurableFieldMultiOption]) RunnableSerializable[Input, Output]

Configure particular Runnable fields at runtime.

Parameters

**kwargs (Union[ConfigurableField, ConfigurableFieldSingleOption, ConfigurableFieldMultiOption]) – A dictionary of ConfigurableField instances to configure.

Returns

A new Runnable with the fields configured.

Return type

RunnableSerializable[Input, Output]

from langchain_core.runnables import ConfigurableField
from langchain_openai import ChatOpenAI

model = ChatOpenAI(max_tokens=20).configurable_fields(
    max_tokens=ConfigurableField(
        id="output_token_number",
        name="Max tokens in the output",
        description="The maximum number of tokens in the output",
    )
)

# max_tokens = 20
print(
    "max_tokens_20: ",
    model.invoke("tell me something about chess").content
)

# max_tokens = 200
print("max_tokens_200: ", model.with_config(
    configurable={"output_token_number": 200}
    ).invoke("tell me something about chess").content
)
generate(messages: List[List[BaseMessage]], stop: Optional[List[str]] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, *, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, run_name: Optional[str] = None, run_id: Optional[UUID] = None, **kwargs: Any) LLMResult

Pass a sequence of prompts to the model and return model generations.

This method should make use of batched calls for models that expose a batched API.

Use this method when you want to:
  1. take advantage of batched calls,

  2. need more output from the model than just the top generated value,

  3. are building chains that are agnostic to the underlying language model

    type (e.g., pure text completion models vs chat models).

Parameters
  • messages (List[List[BaseMessage]]) – List of list of messages.

  • stop (Optional[List[str]]) – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

  • callbacks (Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]) – Callbacks to pass through. Used for executing additional functionality, such as logging or streaming, throughout generation.

  • **kwargs (Any) – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

  • tags (Optional[List[str]]) –

  • metadata (Optional[Dict[str, Any]]) –

  • run_name (Optional[str]) –

  • run_id (Optional[UUID]) –

  • **kwargs

Returns

An LLMResult, which contains a list of candidate Generations for each input

prompt and additional model provider-specific output.

Return type

LLMResult

generate_prompt(prompts: List[PromptValue], stop: Optional[List[str]] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) LLMResult

Pass a sequence of prompts to the model and return model generations.

This method should make use of batched calls for models that expose a batched API.

Use this method when you want to:
  1. take advantage of batched calls,

  2. need more output from the model than just the top generated value,

  3. are building chains that are agnostic to the underlying language model

    type (e.g., pure text completion models vs chat models).

Parameters
  • prompts (List[PromptValue]) – List of PromptValues. A PromptValue is an object that can be converted to match the format of any language model (string for pure text generation models and BaseMessages for chat models).

  • stop (Optional[List[str]]) – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

  • callbacks (Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]) – Callbacks to pass through. Used for executing additional functionality, such as logging or streaming, throughout generation.

  • **kwargs (Any) – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

An LLMResult, which contains a list of candidate Generations for each input

prompt and additional model provider-specific output.

Return type

LLMResult

get_num_tokens(text: str) int

Get the number of tokens present in the text.

Useful for checking if an input fits in a model’s context window.

Parameters

text (str) – The string input to tokenize.

Returns

The integer number of tokens in the text.

Return type

int

get_num_tokens_from_messages(messages: List[BaseMessage]) int

Get the number of tokens in the messages.

Useful for checking if an input fits in a model’s context window.

Parameters

messages (List[BaseMessage]) – The message inputs to tokenize.

Returns

The sum of the number of tokens across the messages.

Return type

int

get_token_ids(text: str) List[int]

Return the ordered ids of the tokens in a text.

Parameters

text (str) – The string input to tokenize.

Returns

A list of ids corresponding to the tokens in the text, in order they occur

in the text.

Return type

List[int]

invoke(input: LanguageModelInput, config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) BaseMessage

Transform a single input into an output. Override to implement.

Parameters
  • input (LanguageModelInput) – The input to the Runnable.

  • config (Optional[RunnableConfig]) – A config to use when invoking the Runnable. The config supports standard keys like ‘tags’, ‘metadata’ for tracing purposes, ‘max_concurrency’ for controlling how much work to do in parallel, and other keys. Please refer to the RunnableConfig for more details.

  • stop (Optional[List[str]]) –

  • kwargs (Any) –

Returns

The output of the Runnable.

Return type

BaseMessage

predict(text: str, *, stop: Optional[Sequence[str]] = None, **kwargs: Any) str

Deprecated since version langchain-core==0.1.7: Use invoke instead.

Parameters
  • text (str) –

  • stop (Optional[Sequence[str]]) –

  • kwargs (Any) –

Return type

str

predict_messages(messages: List[BaseMessage], *, stop: Optional[Sequence[str]] = None, **kwargs: Any) BaseMessage

Deprecated since version langchain-core==0.1.7: Use invoke instead.

Parameters
  • messages (List[BaseMessage]) –

  • stop (Optional[Sequence[str]]) –

  • kwargs (Any) –

Return type

BaseMessage

stream(input: LanguageModelInput, config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) Iterator[BaseMessageChunk]

Default implementation of stream, which calls invoke. Subclasses should override this method if they support streaming output.

Parameters
  • input (LanguageModelInput) – The input to the Runnable.

  • config (Optional[RunnableConfig]) – The config to use for the Runnable. Defaults to None.

  • kwargs (Any) – Additional keyword arguments to pass to the Runnable.

  • stop (Optional[List[str]]) –

Yields

The output of the Runnable.

Return type

Iterator[BaseMessageChunk]

to_json() Union[SerializedConstructor, SerializedNotImplemented]

Serialize the Runnable to JSON.

Returns

A JSON-serializable representation of the Runnable.

Return type

Union[SerializedConstructor, SerializedNotImplemented]

with_structured_output(schema: Union[Dict, Type[BaseModel]], *, include_raw: bool = False, **kwargs: Any) Runnable[Union[PromptValue, str, Sequence[Union[BaseMessage, List[str], Tuple[str, str], str, Dict[str, Any]]]], Union[Dict, BaseModel]][source]

Model wrapper that returns outputs formatted to match the given schema.

Parameters
  • schema (Union[Dict, Type[BaseModel]]) –

    The output schema. Can be passed in as:
    • an Anthropic tool schema,

    • an OpenAI function/tool schema,

    • a JSON Schema,

    • a TypedDict class (support added in 0.1.22),

    • or a Pydantic class.

    If schema is a Pydantic class then the model output will be a Pydantic instance of that class, and the model-generated fields will be validated by the Pydantic class. Otherwise the model output will be a dict and will not be validated. See langchain_core.utils.function_calling.convert_to_openai_tool() for more on how to properly specify types and descriptions of schema fields when specifying a Pydantic or TypedDict class.

    Changed in version 0.1.22: Added support for TypedDict class.

  • include_raw (bool) – If False then only the parsed structured output is returned. If an error occurs during model output parsing it will be raised. If True then both the raw model response (a BaseMessage) and the parsed model response will be returned. If an error occurs during output parsing it will be caught and returned as well. The final output is always a dict with keys “raw”, “parsed”, and “parsing_error”.

  • kwargs (Any) –

Returns

A Runnable that takes same inputs as a langchain_core.language_models.chat.BaseChatModel.

If include_raw is False and schema is a Pydantic class, Runnable outputs an instance of schema (i.e., a Pydantic object).

Otherwise, if include_raw is False then Runnable outputs a dict.

If include_raw is True, then Runnable outputs a dict with keys:
  • "raw": BaseMessage

  • "parsed": None if there was a parsing error, otherwise the type depends on the schema as described above.

  • "parsing_error": Optional[BaseException]

Return type

Runnable[Union[PromptValue, str, Sequence[Union[BaseMessage, List[str], Tuple[str, str], str, Dict[str, Any]]]], Union[Dict, BaseModel]]

Example: Pydantic schema (include_raw=False):
from langchain_anthropic import ChatAnthropic
from langchain_core.pydantic_v1 import BaseModel

class AnswerWithJustification(BaseModel):
    '''An answer to the user question along with justification for the answer.'''
    answer: str
    justification: str

llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
structured_llm = llm.with_structured_output(AnswerWithJustification)

structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")

# -> AnswerWithJustification(
#     answer='They weigh the same',
#     justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'
# )
Example: Pydantic schema (include_raw=True):
from langchain_anthropic import ChatAnthropic
from langchain_core.pydantic_v1 import BaseModel

class AnswerWithJustification(BaseModel):
    '''An answer to the user question along with justification for the answer.'''
    answer: str
    justification: str

llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
structured_llm = llm.with_structured_output(AnswerWithJustification, include_raw=True)

structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
# -> {
#     'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Ao02pnFYXD6GN1yzc0uXPsvF', 'function': {'arguments': '{"answer":"They weigh the same.","justification":"Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ."}', 'name': 'AnswerWithJustification'}, 'type': 'function'}]}),
#     'parsed': AnswerWithJustification(answer='They weigh the same.', justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'),
#     'parsing_error': None
# }
Example: Dict schema (include_raw=False):
from langchain_anthropic import ChatAnthropic

schema = {
    "name": "AnswerWithJustification",
    "description": "An answer to the user question along with justification for the answer.",
    "input_schema": {
        "type": "object",
        "properties": {
            "answer": {"type": "string"},
            "justification": {"type": "string"},
        },
        "required": ["answer", "justification"]
    }
}
llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
structured_llm = llm.with_structured_output(schema)

structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
# -> {
#     'answer': 'They weigh the same',
#     'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.'
# }

Examples using ChatAnthropic