Skip to main content
您可以在 Claude 文档中找到 Anthropic 最新模型的信息,包括其费用、上下文窗口和支持的输入类型。
API 参考有关所有功能和配置选项的详细文档,请参阅 ChatAnthropic API 参考。
AWS Bedrock 和 Google VertexAI请注意,某些 Anthropic 模型也可以通过 AWS Bedrock 和 Google VertexAI 访问。请参阅 ChatBedrockChatVertexAI 集成,通过这些服务使用 Anthropic 模型。对于 AWS Bedrock 上使用与 ChatAnthropic 相同 API 的 Anthropic 模型,请使用 langchain-aws 中的 ChatAnthropicBedrock

概述

集成详情

可序列化JS/TS 支持下载量最新版本
ChatAnthropiclangchain-anthropicbeta(npm)Downloads per monthPyPI - Latest version

模型功能

工具调用结构化输出图像输入音频输入视频输入逐词流式传输原生异步Token 使用量对数概率

设置

要访问 Anthropic(Claude)模型,您需要安装 langchain-anthropic 集成包并获取 Claude API 密钥。

安装

pip install -U langchain-anthropic

凭证

前往 Claude 控制台 注册并生成 Claude API 密钥。完成后设置 ANTHROPIC_API_KEY 环境变量:
import getpass
import os

if "ANTHROPIC_API_KEY" not in os.environ:
    os.environ["ANTHROPIC_API_KEY"] = getpass.getpass("Enter your Anthropic API key: ")
要启用模型调用的自动追踪,请设置您的 LangSmith API 密钥:
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

实例化

现在我们可以实例化模型对象并生成聊天补全:
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(
    model="claude-haiku-4-5-20251001",
    # temperature=,
    # max_tokens=,
    # timeout=,
    # max_retries=,
    # ...
)
有关所有可用实例化参数的详细信息,请参阅 ChatAnthropic API 参考。

调用

messages = [
    (
        "system",
        "You are a helpful translator. Translate the user sentence to French.",
    ),
    (
        "human",
        "I love programming.",
    ),
]
model.invoke(messages)
print(ai_msg.text)
J'adore la programmation.
for chunk in model.stream(messages):
    print(chunk.text, end="")
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")
要从流中聚合完整消息:
stream = model.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")
await model.ainvoke(messages)

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

# batch
await model.abatch([messages])
AIMessage(
    content="J'aime la programmation.",
    response_metadata={
        "id": "msg_01Trik66aiQ9Z1higrD5XFx3",
        "model": "claude-sonnet-4-6",
        "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,
    },
)
在我们的模型指南中了解更多关于支持的调用方法。

内容块

在使用工具、扩展思考和其他功能时,单个 Anthropic AIMessage 的内容可以是单个字符串或 Anthropic 内容块列表。 例如,当 Anthropic 模型调用工具时,工具调用是消息内容的一部分(同时也暴露在标准化的 AIMessage.tool_calls 中):
from langchain_anthropic import ChatAnthropic
from typing_extensions import Annotated

model = ChatAnthropic(model="claude-haiku-4-5-20251001")


def get_weather(
    location: Annotated[str, ..., "Location as city and state."]
) -> str:
    """Get the weather at a location."""
    return "It's sunny."


model_with_tools = model.bind_tools([get_weather])
response = model_with_tools.invoke("Which city is hotter today: LA or NY?")
response.content
[{'text': "I'll help you compare the temperatures of Los Angeles and New York by checking their current weather. I'll retrieve the weather for both cities.",
  'type': 'text'},
 {'id': 'toolu_01CkMaXrgmsNjTso7so94RJq',
  'input': {'location': 'Los Angeles, CA'},
  'name': 'get_weather',
  'type': 'tool_use'},
 {'id': 'toolu_01SKaTBk9wHjsBTw5mrPVSQf',
  'input': {'location': 'New York, NY'},
  'name': 'get_weather',
  'type': 'tool_use'}]
使用 content_blocks 将以 LangChain 的标准格式渲染内容,该格式在其他模型提供商之间保持一致。了解更多关于内容块的信息。
response.content_blocks
您也可以使用 tool_calls 属性以标准格式专门访问工具调用:
response.tool_calls
[{'name': 'GetWeather',
  'args': {'location': 'Los Angeles, CA'},
  'id': 'toolu_01Ddzj5PkuZkrjF4tafzu54A'},
 {'name': 'GetWeather',
  'args': {'location': 'New York, NY'},
  'id': 'toolu_012kz4qHZQqD4qg8sFPeKqpP'}]

工具

Anthropic 的工具使用功能允许您定义 Claude 在对话过程中可以调用的外部函数。这使得动态信息检索、计算以及与外部系统的交互成为可能。 有关如何将工具绑定到模型实例的详细信息,请参阅 ChatAnthropic.bind_tools
有关 Claude 内置工具(代码执行、网页浏览、Files API 等)的信息,请参阅内置工具
from pydantic 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")


model_with_tools = model.bind_tools([GetWeather, GetPopulation])
ai_msg = model_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",
    },
]

严格工具使用

严格工具使用需要:
  • Claude Sonnet 4.5 或 Opus 4.1.
  • langchain-anthropic>=1.1.0
Anthropic 支持可选择启用的工具调用严格模式约束。这通过约束解码保证工具名称和参数经过验证且类型正确。 在非严格模式下,Claude 有时会生成无效的工具输入,导致应用程序出错:
  • 类型不匹配passengers: "2" 而非 passengers: 2
  • 缺少必需字段:省略函数期望的字段
  • 无效枚举值:超出允许集的值
  • 模式违规:嵌套对象不匹配预期结构
严格工具使用保证符合模式的工具调用:
  • 工具输入严格遵循您的 input_schema
  • 保证字段类型和必需字段
  • 消除格式错误输入的错误处理
  • 使用的工具 name 始终来自提供的工具
使用严格工具模式使用标准工具调用
构建可靠性至关重要的智能体工作流简单的单轮工具调用
具有许多参数或嵌套对象的工具原型设计和实验
需要特定类型的函数(例如 intstr
要启用严格工具使用,请在调用 bind_tools 时指定 strict=True
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-sonnet-4-6")

def get_weather(location: str) -> str:
    """Get the weather at a location."""
    return "It's sunny."

model_with_tools = model.bind_tools([get_weather], strict=True)
考虑一个 passengers 必须是整数的预订系统:
from langchain_anthropic import ChatAnthropic
from typing import Literal

model = ChatAnthropic(model="claude-sonnet-4-6")

def book_flight(
    destination: str,
    departure_date: str,
    passengers: int,
    cabin_class: Literal["economy", "business", "first"]
) -> str:
    """Book a flight to a destination.

    Args:
        destination: The destination city
        departure_date: Date in YYYY-MM-DD format
        passengers: Number of passengers (must be an integer)
        cabin_class: The cabin class for the flight
    """
    return f"Booked {passengers} passengers to {destination}"

model_with_tools = model.bind_tools(
    [book_flight],
    strict=True,
    tool_choice="any",
)
response = model_with_tools.invoke("Book 2 passengers to Tokyo, business class, 2025-01-15")

# With strict=True, passengers is guaranteed to be int, not "2" or "two"
print(response.tool_calls[0]["args"]["passengers"])
2
严格工具使用有一些需要注意的 JSON 模式限制。更多详情请参阅 Claude 文档 如果您的工具模式使用了不支持的功能,将收到 400 错误。在这种情况下,请简化模式或使用标准(非严格)工具调用。

输入示例

对于复杂工具,您可以提供使用示例帮助 Claude 正确理解如何使用它们。这通过在工具的 extras 参数中设置 input_examples 来实现。
from langchain_anthropic import ChatAnthropic
from langchain.tools import tool

@tool(
    extras={
        "input_examples": [
            {
                "query": "weather report",
                "location": "San Francisco",
                "format": "detailed"
            },
            {
                "query": "temperature",
                "location": "New York",
                "format": "brief"
            }
        ]
    }
)
def search_weather_data(query: str, location: str, format: str = "brief") -> str:
    """Search weather database with specific query and format preferences.

    Args:
        query: The type of weather information to retrieve
        location: City or region to search
        format: Output format, either 'brief' or 'detailed'
    """
    return f"{format.title()} {query} for {location}: Data found"

model = ChatAnthropic(model="claude-sonnet-4-6")
model_with_tools = model.bind_tools([search_weather_data])

response = model_with_tools.invoke(
    "Get me a detailed weather report for Seattle"
)
extras 参数还支持:

细粒度工具流式传输

Anthropic 支持细粒度工具流式传输,这是一个减少具有大型参数的工具调用流式传输延迟的测试版功能。 细粒度流式传输不是在传输前缓冲整个参数值,而是在数据可用时立即发送。对于大型工具参数,这可以将初始延迟从 15 秒减少到约 3 秒。
细粒度流式传输可能返回无效或不完整的 JSON 输入,特别是当响应在完成前达到 max_tokens 时。请为不完整的 JSON 数据实现适当的错误处理。
要启用细粒度工具流式传输,请在初始化模型时指定 fine-grained-tool-streaming-2025-05-14 测试版头:
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(
    model="claude-sonnet-4-6",
    betas=["fine-grained-tool-streaming-2025-05-14"],
)

def write_document(title: str, content: str) -> str:
    """Write a document with the given title and content."""
    return f"Document '{title}' written successfully"

model_with_tools = model.bind_tools([write_document])

# Stream tool calls with reduced latency
for chunk in model_with_tools.stream(
    "Write a detailed technical document about the benefits of streaming APIs"
):
    print(chunk.content)
流式数据作为 chunk.content 中的 input_json_delta 块到达。您可以累积这些数据以构建完整的工具参数:
import json

accumulated_json = ""

for chunk in model_with_tools.stream("Write a document about AI"):
    for block in chunk.content:
        if isinstance(block, dict) and block.get("type") == "input_json_delta":
            accumulated_json += block.get("partial_json", "")
            try:
                # Try to parse accumulated JSON
                parsed = json.loads(accumulated_json)
                print(f"Complete args: {parsed}")
            except json.JSONDecodeError:
                # JSON is still incomplete, continue accumulating
                pass
Complete args: {'title': 'Artificial Intelligence: An Overview', 'content': '# Artificial Intelligence: An Overview...

程序化工具调用

程序化工具调用需要:
  • Claude Sonnet 4.5 或 Opus 4.5.
  • langchain-anthropic>=1.3.0
您必须指定 advanced-tool-use-2025-11-20 测试版头以启用程序化工具调用。
工具可以配置为可从 Claude 的代码执行环境中调用,在涉及大型数据处理或多工具工作流的场景中减少延迟和令牌消耗。 有关详细信息,请参阅 Claude 的程序化工具调用指南。要使用此功能:
  • 在工具集中包含代码执行内置工具
  • 在希望以程序化方式调用的工具上指定 extras={"allowed_callers": ["code_execution_20250825"]}
请参阅下面的 create_agent 完整示例。
您可以在初始化时指定 reuse_last_container 以自动重用来自先前模型响应的代码执行容器。
from langchain.agents import create_agent
from langchain.tools import tool
from langchain_anthropic import ChatAnthropic


@tool(extras={"allowed_callers": ["code_execution_20250825"]})
def get_weather(location: str) -> str:
    """Get the weather at a location."""
    return "It's sunny."

tools = [
    {"type": "code_execution_20250825", "name": "code_execution"},
    get_weather,
]

model = ChatAnthropic(
    model="claude-sonnet-4-5",
    betas=["advanced-tool-use-2025-11-20"],
    reuse_last_container=True,
)

agent = create_agent(model, tools=tools)

input_query = {
    "role": "user",
    "content": "What's the weather in Boston?",
}

result = agent.invoke({"messages": [input_query]})

多模态

Claude 支持将图像和 PDF 作为内容块输入,既支持 Anthropic 的原生格式(请参阅视觉PDF 支持的文档),也支持 LangChain 的标准格式

支持的输入方式

方式图像PDF
Base64 内联数据
HTTP/HTTPS URL
Files API
Files API 也可用于将文件上传到容器,以供 Claude 的内置代码执行工具使用。有关详细信息,请参阅代码执行部分。

图像输入

使用带有列表内容格式的 HumanMessage 提供图像输入以及文本。
from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage

model = ChatAnthropic(model="claude-sonnet-4-6")

message = HumanMessage(
    content=[
        {"type": "text", "text": "Describe the image at the URL."},
        {
            "type": "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",
        },
    ]
)
response = model.invoke([message])

PDF 输入

提供 PDF 文件输入以及文本。
from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage

model = ChatAnthropic(model="claude-sonnet-4-6")

message = HumanMessage(
    content=[
        {"type": "text", "text": "Summarize this document."},
        {
            "type": "file",
            "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
            "mime_type": "application/pdf",
        },
    ]
)
response = model.invoke([message])

扩展思考

部分 Claude 模型支持扩展思考功能,该功能将输出得出最终答案的逐步推理过程。 Claude 文档中查看兼容模型。 要使用扩展思考,请在初始化 ChatAnthropic 时指定 thinking 参数。如需要,也可以在调用时作为参数传入。 对于 Claude Sonnet 及更早版本的模型,您需要指定令牌预算。对于 Claude Opus 4.6+,可以使用自适应思考,该功能会自动确定预算。
import json
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(
    model="claude-sonnet-4-6",
    max_tokens=5000,
    thinking={"type": "enabled", "budget_tokens": 2000},
)

response = model.invoke("What is the cube root of 50.653?")
print(json.dumps(response.content_blocks, indent=2))
[
  {
    "type": "reasoning",
    "reasoning": "To find the cube root of 50.653, I need to find the value of $x$ such that $x^3 = 50.653$.\n\nI can try to estimate this first. \n$3^3 = 27$\n$4^3 = 64$\n\nSo the cube root of 50.653 will be somewhere between 3 and 4, but closer to 4.\n\nLet me try to compute this more precisely. I can use the cube root function:\n\ncube root of 50.653 = 50.653^(1/3)\n\nLet me calculate this:\n50.653^(1/3) \u2248 3.6998\n\nLet me verify:\n3.6998^3 \u2248 50.6533\n\nThat's very close to 50.653, so I'm confident that the cube root of 50.653 is approximately 3.6998.\n\nActually, let me compute this more precisely:\n50.653^(1/3) \u2248 3.69981\n\nLet me verify once more:\n3.69981^3 \u2248 50.652998\n\nThat's extremely close to 50.653, so I'll say that the cube root of 50.653 is approximately 3.69981.",
    "extras": {"signature": "ErUBCkYIBxgCIkB0UjV..."}
  },
  {
    "type": "text",
    "text": "The cube root of 50.653 is approximately 3.6998.\n\nTo verify: 3.6998\u00b3 = 50.6530, which is very close to our original number.",
  }
]
Claude Messages API 在 Claude Sonnet 3.7 和 Claude 4 模型之间以不同方式处理思考。更多信息请参阅 Claude 文档

努力程度

某些 Claude 模型支持努力程度功能,用于控制 Claude 响应时使用的令牌数量。这对于平衡响应质量与延迟和成本非常有用。
模型支持
  • 正式可用:Claude Opus 4.6 和 Claude Opus 4.5
  • max 努力程度级别仅受 Claude Opus 4.6 支持
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(
    model="claude-opus-4-5-20251101",
    effort="medium",  # Options: "max", "high", "medium", "low"
)

response = model.invoke("Analyze the trade-offs between microservices and monolithic architectures")
effort 设置为 "high" 与完全省略该参数的行为完全相同。
有关何时使用不同努力程度级别以及支持的模型,请参阅 Claude 文档

引用

Anthropic 支持引用功能,允许 Claude 根据用户提供的源文档将上下文附加到其答案中。 当查询中包含带有 "citations": {"enabled": True}文档search_result 内容块时,Claude 可能会在响应中生成引用。

简单示例

在此示例中,我们传入一个纯文本文档。在后台,Claude 自动将输入文本分块为句子,生成引用时会用到这些句子。
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-haiku-4-5-20251001")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "document",
                "source": {
                    "type": "text",
                    "media_type": "text/plain",
                    "data": "The grass is green. The sky is blue.",
                },
                "title": "My Document",
                "context": "This is a trustworthy document.",
                "citations": {"enabled": True},
            },
            {"type": "text", "text": "What color is the grass and sky?"},
        ],
    }
]
response = model.invoke(messages)
response.content
[{'text': 'Based on the document, ', 'type': 'text'},
 {'text': 'the grass is green',
  'type': 'text',
  'citations': [{'type': 'char_location',
    'cited_text': 'The grass is green. ',
    'document_index': 0,
    'document_title': 'My Document',
    'start_char_index': 0,
    'end_char_index': 20}]},
 {'text': ', and ', 'type': 'text'},
 {'text': 'the sky is blue',
  'type': 'text',
  'citations': [{'type': 'char_location',
    'cited_text': 'The sky is blue.',
    'document_index': 0,
    'document_title': 'My Document',
    'start_char_index': 20,
    'end_char_index': 36}]},
 {'text': '.', 'type': 'text'}]

在工具结果中(智能体 RAG)

Claude 支持 search_result 内容块,代表来自知识库或其他自定义来源查询的可引用结果。这些内容块既可以直接传递给 Claude(如上例),也可以在工具结果中传递。这允许 Claude 使用工具调用结果引用其响应中的元素。 要在响应工具调用时传递搜索结果,请定义一个工具,以 Anthropic 的原生格式返回 search_result 内容块列表。例如:
def retrieval_tool(query: str) -> list[dict]:
    """Access my knowledge base."""

    # Run a search (e.g., with a LangChain vector store)
    results = vector_store.similarity_search(query=query, k=2)

    # Package results into search_result blocks
    return [
        {
            "type": "search_result",
            # Customize fields as desired, using document metadata or otherwise
            "title": "My Document Title",
            "source": "Source description or provenance",
            "citations": {"enabled": True},
            "content": [{"type": "text", "text": doc.page_content}],
        }
        for doc in results
    ]
此处演示一个端到端示例,我们将示例文档填充到 LangChain 向量存储中,并为 Claude 配备一个查询这些文档的工具。此处的工具接受搜索查询和 category 字符串字面量,但可以使用任何有效的工具签名。此示例需要安装 langchain-openainumpy
pip install langchain-openai numpy
from typing import Literal

from langchain.chat_models import init_chat_model
from langchain.embeddings import init_embeddings
from langchain_core.documents import Document
from langchain_core.vectorstores import InMemoryVectorStore
from langgraph.checkpoint.memory import InMemorySaver
from langchain.agents import create_agent


# Set up vector store
# Ensure you set your OPENAI_API_KEY environment variable
embeddings = init_embeddings("openai:text-embedding-3-small")
vector_store = InMemoryVectorStore(embeddings)

document_1 = Document(
    id="1",
    page_content=(
        "To request vacation days, submit a leave request form through the "
        "HR portal. Approval will be sent by email."
    ),
    metadata={
        "category": "HR Policy",
        "doc_title": "Leave Policy",
        "provenance": "Leave Policy - page 1",
    },
)
document_2 = Document(
    id="2",
    page_content="Managers will review vacation requests within 3 business days.",
    metadata={
        "category": "HR Policy",
        "doc_title": "Leave Policy",
        "provenance": "Leave Policy - page 2",
    },
)
document_3 = Document(
    id="3",
    page_content=(
        "Employees with over 6 months tenure are eligible for 20 paid vacation days "
        "per year."
    ),
    metadata={
        "category": "Benefits Policy",
        "doc_title": "Benefits Guide 2025",
        "provenance": "Benefits Policy - page 1",
    },
)

documents = [document_1, document_2, document_3]
vector_store.add_documents(documents=documents)


# Define tool
async def retrieval_tool(
    query: str, category: Literal["HR Policy", "Benefits Policy"]
) -> list[dict]:
    """Access my knowledge base."""

    def _filter_function(doc: Document) -> bool:
        return doc.metadata.get("category") == category

    results = vector_store.similarity_search(
        query=query, k=2, filter=_filter_function
    )

    return [
        {
            "type": "search_result",
            "title": doc.metadata["doc_title"],
            "source": doc.metadata["provenance"],
            "citations": {"enabled": True},
            "content": [{"type": "text", "text": doc.page_content}],
        }
        for doc in results
    ]



# Create agent
model = init_chat_model("claude-haiku-4-5-20251001")

checkpointer = InMemorySaver()
agent = create_agent(model, [retrieval_tool], checkpointer=checkpointer)


# Invoke on a query
config = {"configurable": {"thread_id": "session_1"}}

input_message = {
    "role": "user",
    "content": "How do I request vacation days?",
}
async for step in agent.astream(
    {"messages": [input_message]},
    config,
    stream_mode="values",
):
    step["messages"][-1].pretty_print()

与文本分割器一起使用

Anthropic 还允许您使用自定义文档类型指定自己的分割方式。LangChain 文本分割器可用于生成有意义的分割。请参阅下面的示例,我们将 LangChain README.md(一个 Markdown 文档)分割并作为上下文传递给 Claude: 此示例需要安装 langchain-text-splitters
pip install langchain-text-splitters
import requests
from langchain_anthropic import ChatAnthropic
from langchain_text_splitters import MarkdownTextSplitter


def format_to_anthropic_documents(documents: list[str]):
    return {
        "type": "document",
        "source": {
            "type": "content",
            "content": [{"type": "text", "text": document} for document in documents],
        },
        "citations": {"enabled": True},
    }


# Pull readme
get_response = requests.get(
    "https://raw.githubusercontent.com/langchain-ai/langchain/master/README.md"
)
readme = get_response.text

# Split into chunks
splitter = MarkdownTextSplitter(
    chunk_overlap=0,
    chunk_size=50,
)
documents = splitter.split_text(readme)

# Construct message
message = {
    "role": "user",
    "content": [
        format_to_anthropic_documents(documents),
        {"type": "text", "text": "Give me a link to LangChain's tutorials."},
    ],
}

# Query model
model = ChatAnthropic(model="claude-haiku-4-5-20251001")
response = model.invoke([message])

提示词缓存

Anthropic 支持对提示词元素进行缓存,包括消息、工具定义、工具结果、图像和文档。这允许您重用大型文档、指令、少样本文档和其他数据,以减少延迟和成本。 要启用提示词元素的缓存,请使用 cache_control 键标记其关联的内容块。请参阅以下示例:
只有某些 Claude 模型支持提示词缓存。有关详细信息,请参阅 Claude 文档

消息

import requests
from langchain_anthropic import ChatAnthropic


model = ChatAnthropic(model="claude-sonnet-4-6")

# Pull LangChain readme
get_response = requests.get(
    "https://raw.githubusercontent.com/langchain-ai/langchain/master/README.md"
)
readme = get_response.text

messages = [
    {
        "role": "system",
        "content": [
            {
                "type": "text",
                "text": "You are a technology expert.",
            },
            {
                "type": "text",
                "text": f"{readme}",
                "cache_control": {"type": "ephemeral"},
            },
        ],
    },
    {
        "role": "user",
        "content": "What's LangChain, according to its README?",
    },
]

response_1 = model.invoke(messages)
response_2 = model.invoke(messages)

usage_1 = response_1.usage_metadata["input_token_details"]
usage_2 = response_2.usage_metadata["input_token_details"]

print(f"First invocation:\n{usage_1}")
print(f"\nSecond:\n{usage_2}")
First invocation:
{'cache_read': 0, 'cache_creation': 1458}

Second:
{'cache_read': 1458, 'cache_creation': 0}
或者,您可以在调用时启用提示词缓存。您可能希望根据运行时条件(例如上下文长度)有条件地进行缓存。这对于应用程序级别关于缓存内容的决策非常有用。
response = model.invoke(
    messages,
    cache_control={"type": "ephemeral"},
)
扩展缓存缓存生命周期默认为 5 分钟。如果这太短,可以通过启用 "extended-cache-ttl-2025-04-11" 测试版头并在消息上指定 "cache_control": {"type": "ephemeral", "ttl": "1h"} 来应用一小时缓存。
model = ChatAnthropic(
    model="claude-sonnet-4-6",
    betas=["extended-cache-ttl-2025-04-11"],
)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": f"{long_text}",
                "cache_control": {"type": "ephemeral", "ttl": "1h"},
            },
        ],
    }
]
缓存令牌数量的详细信息将包含在响应的 usage_metadataInputTokenDetails 中:
response = model.invoke(messages)
response.usage_metadata
{
    "input_tokens": 1500,
    "output_tokens": 200,
    "total_tokens": 1700,
    "input_token_details": {
        "cache_read": 0,
        "cache_creation": 1000,
        "ephemeral_1h_input_tokens": 750,
        "ephemeral_5m_input_tokens": 250,
    }
}

缓存工具

from langchain_anthropic import ChatAnthropic
from langchain.tools import tool


# For demonstration purposes, we artificially expand the
# tool description.
description = (
    "Get the weather at a location. "
    f"By the way, check out this readme: {readme}"
)


@tool(description=description, extras={"cache_control": {"type": "ephemeral"}})
def get_weather(location: str) -> str:
    return "It's sunny."


model = ChatAnthropic(model="claude-sonnet-4-6")
model_with_tools = model.bind_tools([get_weather])
query = "What's the weather in San Francisco?"

response_1 = model_with_tools.invoke(query)
response_2 = model_with_tools.invoke(query)

usage_1 = response_1.usage_metadata["input_token_details"]
usage_2 = response_2.usage_metadata["input_token_details"]

print(f"First invocation:\n{usage_1}")
print(f"\nSecond:\n{usage_2}")
First invocation:
{'cache_read': 0, 'cache_creation': 1809}

Second:
{'cache_read': 1809, 'cache_creation': 0}

对话应用中的增量缓存

提示词缓存可用于多轮对话,以保持早期消息的上下文而无需冗余处理。 我们可以通过用 cache_control 标记最后一条消息来启用增量缓存。Claude 将自动对后续消息使用最长的已缓存前缀。 下面,我们实现了一个集成此功能的简单聊天机器人。我们遵循 LangChain 聊天机器人教程,但添加了一个自定义归约器,该归约器自动用 cache_control 标记每条用户消息中的最后一个内容块:

令牌计数

您可以在将消息发送到模型之前使用 get_num_tokens_from_messages() 计算令牌数。这使用 Anthropic 的官方令牌计数 API
from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage, SystemMessage

model = ChatAnthropic(model="claude-sonnet-4-6")

messages = [
    SystemMessage(content="You are a scientist"),
    HumanMessage(content="Hello, Claude"),
]

token_count = model.get_num_tokens_from_messages(messages)
print(token_count)
14
使用工具时也可以计算令牌数:
from langchain.tools import tool

@tool(parse_docstring=True)
def get_weather(location: str) -> str:
    """Get the current weather in a given location

    Args:
        location: The city and state, e.g. San Francisco, CA
    """
    return "Sunny"

messages = [
    HumanMessage(content="What's the weather like in San Francisco?"),
]

token_count = model.get_num_tokens_from_messages(messages, tools=[get_weather])
print(token_count)
586

上下文管理

Anthropic 支持上下文管理功能,可自动管理模型的上下文窗口以优化性能和成本。 有关更多详细信息和配置选项,请参阅 Claude 文档

清除工具使用

从上下文中清除工具结果以减少令牌使用,同时保持对话流程。
langchain-anthropic>=0.3.21 起支持上下文管理您必须指定 context-management-2025-06-27 测试版头才能对模型调用应用上下文管理。
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(
    model="claude-sonnet-4-6",
    betas=["context-management-2025-06-27"],
    context_management={"edits": [{"type": "clear_tool_uses_20250919"}]},
)
model_with_tools = model.bind_tools([{"type": "web_search_20250305", "name": "web_search"}])
response = model_with_tools.invoke("Search for recent developments in AI")

自动压缩

Claude Opus 4.6 支持自动服务器端压缩,当上下文窗口接近其限制时会智能地压缩对话历史。这允许进行更长的对话而无需手动管理上下文。
自动压缩要求:
  • Claude Opus 4.6
  • langchain-anthropic>=1.3.0
  • compact-2026-01-12 测试版头
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(
    model="claude-opus-4-6",
    betas=["compact-2026-01-12"],
    max_tokens=4096,
    context_management={
        "edits": [
            {
                "type": "compact_20260112",
                "trigger": {"type": "input_tokens", "value": 50000},
            }
        ]
    },
)
有关触发配置的详细信息,请参阅 Anthropic 的文档。 当压缩事件被触发时,ChatAnthropic 将返回代表提示词状态的压缩块。这些内容应保留在多轮应用程序中传回给模型的消息历史记录中。

扩展上下文窗口

某些模型支持 100 万令牌的上下文窗口,目前以测试版形式提供给使用层级 4 的组织和具有自定义速率限制的组织。 要启用扩展上下文窗口,请指定 context-1m-2025-08-07 测试版头:
from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage

model = ChatAnthropic(
    model="claude-sonnet-4-6",
    betas=["context-1m-2025-08-07"],
)

long_document = """
This is a very long document that would benefit from the extended 1M
context window...
[imagine this continues for hundreds of thousands of tokens]
"""

messages = [
    HumanMessage(f"""
Please analyze this document and provide a summary:

{long_document}

What are the key themes and main conclusions?
""")
]

response = model.invoke(messages)
有关详细信息,请参阅 Claude 文档

结构化输出

结构化输出需要:
  • Claude Sonnet 4.5 或 Opus 4.1。
  • langchain-anthropic>=1.1.0
Anthropic 支持原生结构化输出功能,该功能保证其响应符合给定模式。 您可以在单个模型调用中访问此功能,或通过指定 LangChain 智能体响应格式来访问。请参阅下面的示例。
使用 with_structured_output 方法生成结构化模型响应。指定 method="json_schema" 以启用 Anthropic 的原生结构化输出功能;否则该方法默认使用函数调用。
from langchain_anthropic import ChatAnthropic
from pydantic import BaseModel, Field

model = ChatAnthropic(model="claude-sonnet-4-6")

class Movie(BaseModel):
    """A movie with details."""
    title: str = Field(..., description="The title of the movie")
    year: int = Field(..., description="The year the movie was released")
    director: str = Field(..., description="The director of the movie")
    rating: float = Field(..., description="The movie's rating out of 10")

model_with_structure = model.with_structured_output(Movie, method="json_schema")
response = model_with_structure.invoke("Provide details about the movie Inception")
response
Movie(title='Inception', year=2010, director='Christopher Nolan', rating=8.8)
在生成最终响应时,使用 ProviderStrategy 指定 response_format 以启用 Anthropic 的结构化输出功能。
from langchain.agents import create_agent
from langchain.agents.structured_output import ProviderStrategy
from pydantic import BaseModel

class Weather(BaseModel):
    temperature: float
    condition: str

def weather_tool(location: str) -> str:
    """Get the weather at a location."""
    return "Sunny and 75 degrees F."

agent = create_agent(
    model="anthropic:claude-sonnet-4-5",
    tools=[weather_tool],
    response_format=ProviderStrategy(Weather),
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "What's the weather in SF?"}]
})

result["structured_response"]
Weather(temperature=75.0, condition='Sunny')

内置工具

Anthropic 支持各种内置的客户端和服务器端工具 服务器端工具(例如网络搜索)传递给模型并由 Anthropic 执行。客户端工具(例如 bash 工具)需要您在应用程序中实现回调执行逻辑并将结果返回给模型。 在任何情况下,您都可以通过在模型实例上使用 bind_tools 使工具对聊天模型可用。 重要的是,客户端工具需要您实现执行逻辑。请参阅下面的相关部分以获取示例。
中间件与工具对于客户端工具(例如 bash文本编辑器记忆),您可以选择使用中间件,它提供了包含内置执行、状态管理和安全策略的生产就绪实现。当您需要一体化解决方案时使用中间件;当您需要自定义执行逻辑或想直接使用 bind_tools 时使用工具(如下所述)。
测试版工具如果将测试版工具绑定到您的聊天模型,LangChain 将自动为您添加所需的测试版头。

Bash 工具

Claude 支持客户端 bash 工具,允许它在持久性 bash 会话中执行 shell 命令。这支持系统操作、脚本执行和命令行自动化。
重要:您必须提供执行环境LangChain 处理 API 集成(发送/接收工具调用),但您负责
  • 设置沙盒计算环境(Docker、VM 等)
  • 实现命令执行和输出捕获
  • 在智能体循环中将结果传回给 Claude
有关实现指南,请参阅 Claude bash 工具文档
要求:
  • Claude 4 模型或 Claude Sonnet 3.7
import subprocess

from anthropic.types.beta import BetaToolBash20250124Param  
from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage, ToolMessage
from langchain.tools import tool

tool_spec = BetaToolBash20250124Param(
    name="bash",
    type="bash_20250124",
)


@tool(extras={"provider_tool_definition": tool_spec})
def bash(*, command: str, restart: bool = False, **kw):
    """Execute a bash command."""
    if restart:
        return "Bash session restarted"
    try:
        result = subprocess.run(
            command,
            shell=True,
            capture_output=True,
            text=True,
            timeout=30,
        )
        return result.stdout + result.stderr
    except Exception as e:
        return f"Error: {e}"


model = ChatAnthropic(model="claude-sonnet-4-6")
model_with_bash = model.bind_tools([bash])

# Initial request
messages = [HumanMessage("List all files in the current directory")]
response = model_with_bash.invoke(messages)
print(response.content_blocks)

# Tool execution loop
while response.tool_calls:
    # Execute each tool call
    tool_messages = []
    for tool_call in response.tool_calls:
        result = bash.invoke(tool_call)
        tool_messages.append(result)

    # Continue conversation with tool results
    messages = [*messages, response, *tool_messages]
    response = model_with_bash.invoke(messages)
    print(response.content_blocks)
bash 工具支持两个参数:
  • command(必需):要执行的 bash 命令
  • restart(可选):设置为 true 以重启 bash 会话
对于”开箱即用”的实现,请考虑使用 ClaudeBashToolMiddleware,它提供持久会话、Docker 隔离、输出脱敏以及启动/关闭命令。

代码执行

Claude 可以使用服务器端代码执行工具在沙盒环境中执行代码。
Anthropic 的 2025-08-25 代码执行工具从 langchain-anthropic>=1.0.3 起受支持。旧版 2025-05-22 工具从 langchain-anthropic>=0.3.14 起受支持。
代码沙盒没有互联网访问,因此您只能使用环境中预安装的包。有关更多信息,请参阅 Claude 文档
from anthropic.types.beta import BetaCodeExecutionTool20250825Param 
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(
    model="claude-sonnet-4-6",
    # (Optional) Enable the param below to automatically
    # pass back in container IDs from previous response
    reuse_last_container=True,
)

code_tool = BetaCodeExecutionTool20250825Param(
    name="code_execution",
    type="code_execution_20250825",
)
model_with_tools = model.bind_tools([code_tool])

response = model_with_tools.invoke(
    "Calculate the mean and standard deviation of [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]"
)
使用 Files API,Claude 可以编写代码访问文件进行数据分析和其他用途。请参阅以下示例:
import anthropic
from anthropic.types.beta import BetaCodeExecutionTool20250825Param 
from langchain_anthropic import ChatAnthropic


client = anthropic.Anthropic()
file = client.beta.files.upload(
    file=open("/path/to/sample_data.csv", "rb")
)
file_id = file.id


# Run inference
model = ChatAnthropic(
    model="claude-sonnet-4-6",
)

code_tool = BetaCodeExecutionTool20250825Param(
    name="code_execution",
    type="code_execution_20250825",
)
model_with_tools = model.bind_tools([code_tool])

input_message = {
    "role": "user",
    "content": [
        {
            "type": "text",
            "text": "Please plot these data and tell me what you see.",
        },
        {
            "type": "container_upload",
            "file_id": file_id,
        },
    ]
}
response = model_with_tools.invoke([input_message])
注意 Claude 可能会在代码执行过程中生成文件。您可以使用 Files API 访问这些文件:
# Take all file outputs for demonstration purposes
file_ids = []
for block in response.content:
    if block["type"] == "bash_code_execution_tool_result":
        file_ids.extend(
            content["file_id"]
            for content in block.get("content", {}).get("content", [])
            if "file_id" in content
        )

for i, file_id in enumerate(file_ids):
    file_content = client.beta.files.download(file_id)
    file_content.write_to_file(f"/path/to/file_{i}.png")
可用工具版本:
  • code_execution_20250522(旧版)
  • code_execution_20250825(推荐)

计算机操控

Claude 支持客户端计算机操控功能,允许通过截图、鼠标控制和键盘输入与桌面环境交互。
重要:您必须提供执行环境LangChain 处理 API 集成(发送/接收工具调用),但您负责
  • 设置沙盒计算环境(Linux VM、Docker 容器等)
  • 实现虚拟显示器(例如 Xvfb)
  • 执行 Claude 的工具调用(截图、鼠标点击、键盘输入)
  • 在智能体循环中将结果传回给 Claude
Anthropic 提供了一个参考实现帮助您入门。
要求:
  • Claude Opus 4.5、Claude 4 或 Claude Sonnet 3.7
import base64
from typing import Literal

from anthropic.types.beta import BetaToolComputerUse20250124Param 
from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage, ToolMessage
from langchain.tools import tool

DISPLAY_WIDTH = 1024
DISPLAY_HEIGHT = 768

tool_spec = BetaToolComputerUse20250124Param(
    name="computer",
    type="computer_20250124",
    display_width_px=DISPLAY_WIDTH,
    display_height_px=DISPLAY_HEIGHT,
    display_number=1,
)

@tool(extras={"provider_tool_definition": tool_spec})
def computer(
    *,
    action: Literal[
        "key", "type", "mouse_move", "left_click", "left_click_drag",
        "right_click", "middle_click", "double_click", "screenshot",
        "cursor_position", "scroll"
    ],
    coordinate: list[int] | None = None,
    text: str | None = None,
    **kw
):
    """Control the computer display."""
    if action == "screenshot":
        # Take screenshot and return base64-encoded image
        # Implementation depends on your display setup (e.g., Xvfb, pyautogui)
        return {"type": "image", "data": "base64_screenshot_data..."}
    elif action == "left_click" and coordinate:
        # Execute click at coordinate
        return f"Clicked at {coordinate}"
    elif action == "type" and text:
        # Type text
        return f"Typed: {text}"
    # ... implement other actions
    return f"Executed {action}"

model = ChatAnthropic(model="claude-sonnet-4-6")
model_with_computer = model.bind_tools([computer])

# Initial request
messages = [HumanMessage("Take a screenshot to see what's on the screen")]
response = model_with_computer.invoke(messages)
print(response.content_blocks)

# Tool execution loop
while response.tool_calls:
    tool_messages = []
    for tool_call in response.tool_calls:
        result = computer.invoke(tool_call["args"])
        tool_messages.append(
            ToolMessage(content=str(result), tool_call_id=tool_call["id"])
        )

    messages = [*messages, response, *tool_messages]
    response = model_with_computer.invoke(messages)
    print(response.content_blocks)
可用工具版本:
  • computer_20250124(适用于 Claude 4 和 Claude Sonnet 3.7)
  • computer_20251124(适用于 Claude Opus 4.5)

远程 MCP

Claude 可以使用服务器端 MCP 连接器工具对远程 MCP 服务器进行模型生成的调用。
远程 MCP 从 langchain-anthropic>=0.3.14 起受支持
from anthropic.types.beta import BetaMCPToolsetParam 
from langchain_anthropic import ChatAnthropic

mcp_servers = [
    {
        "type": "url",
        "url": "https://docs.langchain.com/mcp",
        "name": "LangChain Docs",
    }
]

model = ChatAnthropic(
    model="claude-sonnet-4-6",
    mcp_servers=mcp_servers,
)

mcp_tool = BetaMCPToolsetParam(
    type="mcp_toolset",
    mcp_server_name="LangChain Docs",
)

response = model.invoke(
    "What are LangChain content blocks?",
    tools=[mcp_tool],
)

文本编辑器

Claude 支持客户端文本编辑器工具,可用于查看和修改本地文本文件。详细信息请参阅此处的文档。
from typing import Literal

from anthropic.types.beta import BetaToolTextEditor20250728Param 
from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage, ToolMessage
from langchain.tools import tool

tool_spec = BetaToolTextEditor20250728Param(
    name="str_replace_based_edit_tool",
    type="text_editor_20250728",
)

# Simple in-memory file storage for demonstration
files: dict[str, str] = {
    "/workspace/primes.py": "def is_prime(n):\n    if n < 2\n        return False\n    return True"
}

@tool(extras={"provider_tool_definition": tool_spec})
def str_replace_based_edit_tool(
    *,
    command: Literal["view", "create", "str_replace", "insert", "undo_edit"],
    path: str,
    file_text: str | None = None,
    old_str: str | None = None,
    new_str: str | None = None,
    insert_line: int | None = None,
    view_range: list[int] | None = None,
    **kw
):
    """View and edit text files."""
    if command == "view":
        if path not in files:
            return f"Error: File {path} not found"
        content = files[path]
        if view_range:
            lines = content.splitlines()
            start, end = view_range[0] - 1, view_range[1]
            return "\n".join(lines[start:end])
        return content
    elif command == "create":
        files[path] = file_text or ""
        return f"Created {path}"
    elif command == "str_replace" and old_str is not None:
        if path not in files:
            return f"Error: File {path} not found"
        files[path] = files[path].replace(old_str, new_str or "", 1)
        return f"Replaced in {path}"
    # ... implement other commands
    return f"Executed {command} on {path}"

model = ChatAnthropic(model="claude-sonnet-4-6")
model_with_tools = model.bind_tools([str_replace_based_edit_tool])

# Initial request
messages = [HumanMessage("There's a syntax error in my primes.py file. Can you fix it?")]
response = model_with_tools.invoke(messages)
print(response.content_blocks)

# Tool execution loop
while response.tool_calls:
    tool_messages = []
    for tool_call in response.tool_calls:
        result = str_replace_based_edit_tool.invoke(tool_call["args"])
        tool_messages.append(
            ToolMessage(content=result, tool_call_id=tool_call["id"])
        )

    messages = [*messages, response, *tool_messages]
    response = model_with_tools.invoke(messages)
    print(response.content_blocks)
可用工具版本:
  • text_editor_20250124(旧版)
  • text_editor_20250728(推荐)
对于”开箱即用”的实现,请考虑使用 StateClaudeTextEditorMiddlewareFilesystemClaudeTextEditorMiddleware,它们提供 LangGraph 状态集成或文件系统持久化、路径验证和其他功能。

网页抓取

Claude 可以使用服务器端网页抓取工具从指定网页和 PDF 文档检索完整内容,并用引用来支撑其响应。
from anthropic.types.beta import BetaWebFetchTool20250910Param 
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-haiku-4-5-20251001")

fetch_tool = BetaWebFetchTool20250910Param(
    name="web_fetch",
    type="web_fetch_20250910",
    max_uses=3,
)

model_with_tools = model.bind_tools([fetch_tool])

response = model_with_tools.invoke(
    "Please analyze the content at https://docs.langchain.com/"
)

网络搜索

Claude 可以使用服务器端网络搜索工具运行搜索并用引用来支撑其响应。
网络搜索工具从 langchain-anthropic>=0.3.13 起受支持
from anthropic.types.beta import BetaWebSearchTool20250305Param 
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-sonnet-4-6")

search_tool = BetaWebSearchTool20250305Param(
    name="web_search",
    type="web_search_20250305",
    max_uses=3,
)

model_with_tools = model.bind_tools([search_tool])

response = model_with_tools.invoke("How do I update a web app to TypeScript 5.5?")

记忆工具

Claude 支持用于跨对话线程在客户端存储和检索上下文的记忆工具。详细信息请参阅此处的文档。
Anthropic 的内置记忆工具从 langchain-anthropic>=0.3.21 起受支持
from typing import Literal

from anthropic.types.beta import BetaMemoryTool20250818Param  
from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage, ToolMessage
from langchain.tools import tool

tool_spec = BetaMemoryTool20250818Param(
    name="memory",
    type="memory_20250818",
)

# Simple in-memory storage for demonstration purposes
memory_store: dict[str, str] = {
    "/memories/interests": "User enjoys Python programming and hiking"
}


@tool(extras={"provider_tool_definition": tool_spec})
def memory(
    *,
    command: Literal["view", "create", "str_replace", "insert", "delete", "rename"],
    path: str,
    content: str | None = None,
    old_str: str | None = None,
    new_str: str | None = None,
    insert_line: int | None = None,
    new_path: str | None = None,
    **kw,
):
    """Manage persistent memory across conversations."""
    if command == "view":
        if path == "/memories":
            # List all memories
            return "\n".join(memory_store.keys()) or "No memories stored"
        return memory_store.get(path, f"No memory at {path}")
    elif command == "create":
        memory_store[path] = content or ""
        return f"Created memory at {path}"
    elif command == "str_replace" and old_str is not None:
        if path in memory_store:
            memory_store[path] = memory_store[path].replace(old_str, new_str or "", 1)
        return f"Updated {path}"
    elif command == "delete":
        memory_store.pop(path, None)
        return f"Deleted {path}"
    # ... implement other commands
    return f"Executed {command} on {path}"


model = ChatAnthropic(model="claude-sonnet-4-6")
model_with_tools = model.bind_tools([memory])

# Initial request
messages = [HumanMessage("What are my interests?")]
response = model_with_tools.invoke(messages)
print(response.content_blocks)

# Tool execution loop
while response.tool_calls:
    tool_messages = []
    for tool_call in response.tool_calls:
        result = memory.invoke(tool_call["args"])
        tool_messages.append(ToolMessage(content=result, tool_call_id=tool_call["id"]))

    messages = [*messages, response, *tool_messages]
    response = model_with_tools.invoke(messages)
    print(response.content_blocks)
[{'type': 'text',
'text': "I'll check my memory to see what information I have about your interests."},
{'type': 'tool_call',
'name': 'memory',
'args': {'command': 'view', 'path': '/memories'},
'id': 'toolu_01XeP9sxx44rcZHFNqXSaKqh'}]
对于”开箱即用”的实现,请考虑使用 StateClaudeMemoryMiddlewareFilesystemClaudeMemoryMiddleware,它们提供 LangGraph 状态集成或文件系统持久化、自动系统提示词注入和其他功能。

工具搜索

Claude 支持服务器端工具搜索功能,该功能支持动态工具发现和加载。Claude 可以搜索您的工具目录并仅加载所需工具,而不是预先将所有工具定义加载到上下文窗口中。 在以下情况下此功能非常有用:
  • 您的系统中有 10 个以上的工具
  • 工具定义消耗了大量令牌
  • 您在大型工具集上遇到工具选择准确性问题
有两种工具搜索变体:
  • 正则表达式 (tool_search_tool_regex_20251119):Claude 构建正则表达式模式来搜索工具
  • BM25 (tool_search_tool_bm25_20251119):Claude 使用自然语言查询来搜索工具
使用 extras 参数在 LangChain 工具上指定 defer_loading
from anthropic.types.beta import BetaToolSearchToolRegex20251119Param 
from langchain_anthropic import ChatAnthropic
from langchain.tools import tool

@tool(extras={"defer_loading": True})
def get_weather(location: str, unit: str = "fahrenheit") -> str:
    """Get the current weather for a location.

    Args:
        location: City name
        unit: Temperature unit (celsius or fahrenheit)
    """
    return f"Weather in {location}: Sunny"

@tool(extras={"defer_loading": True})
def search_files(query: str) -> str:
    """Search through files in the workspace.

    Args:
        query: Search query
    """
    return f"Found files matching '{query}'"

model = ChatAnthropic(model="claude-sonnet-4-6")

tool_search = BetaToolSearchToolRegex20251119Param(
    name="tool_search_tool_regex",
    type="tool_search_tool_regex_20251119",
)

model_with_tools = model.bind_tools([
    tool_search,
    get_weather,
    search_files,
])
response = model_with_tools.invoke("What's the weather in San Francisco?")
关键点:
  • 设置 defer_loading: True 的工具仅在 Claude 通过搜索发现它们时加载
  • 保留您最常用的 3-5 个工具为非延迟加载以获得最佳性能
  • 两种变体都搜索工具名称、描述、参数名称和参数描述
有关工具搜索的更多详细信息,包括与 MCP 服务器和客户端实现的配合使用,请参阅 Claude 文档

响应元数据

ai_msg = model.invoke(messages)
ai_msg.response_metadata
{
    "id": "msg_013xU6FHEGEq76aP4RgFerVT",
    "model": "claude-sonnet-4-6",
    "stop_reason": "end_turn",
    "stop_sequence": None,
    "usage": {"input_tokens": 25, "output_tokens": 11},
}

令牌使用元数据

ai_msg = model.invoke(messages)
ai_msg.usage_metadata
{"input_tokens": 25, "output_tokens": 11, "total_tokens": 36}
默认情况下,流式传输过程中将包含包含令牌使用信息的消息块:
stream = model.stream(messages)
full = next(stream)
for chunk in stream:
    full += chunk
full.usage_metadata
{"input_tokens": 25, "output_tokens": 11, "total_tokens": 36}
可以通过在流方法中或初始化 ChatAnthropic 时设置 stream_usage=False 来禁用这些。

API 参考

有关所有功能和配置选项的详细文档,请参阅 ChatAnthropic API 参考。