ChatAnthropic

本笔记本提供了快速入门Anthropic聊天模型的概述。有关ChatAnthropic所有功能和配置的详细文档，请访问API参考。

Anthropic 有多个聊天模型。你可以在 Anthropic 文档 中找到有关其最新模型的信息，包括成本、上下文窗口和支持的输入类型。

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ChatBedrock和ChatVertexAI集成，以通过这些服务使用Anthropic模型。

概览

集成详情

类	包	本地	可序列化的	JS 支持	软件包下载	最新包裹
ChatAnthropic	langchain-anthropic	❌	beta	✅

模型特性

工具调用	结构化输出	JSON模式	图像输入	音频输入	视频输入	令牌级流式传输	原生异步	令牌使用量	对数概率
✅	✅	❌	✅	❌	❌	✅	✅	✅	❌

设置

要访问Anthropic模型，您需要创建一个Anthropic帐户，获取API密钥，并安装langchain-anthropic集成包。

凭据

前往 https://console.anthropic.com/ 注册Anthropic并生成API密钥。完成后，请设置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跟踪，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"

安装

LangChain Anthropic 集成位于 langchain-anthropic 包中：

%pip install -qU langchain-anthropic

本指南需要 langchain-anthropic>=0.3.10

实例化

现在我们可以实例化我们的模型对象并生成聊天补全：

from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(
    model="claude-3-5-sonnet-20240620",
    temperature=0,
    max_tokens=1024,
    timeout=None,
    max_retries=2,
    # other params...
)

API 参考：ChatAnthropic

调用

messages = [
    (
        "system",
        "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ),
    ("human", "I love programming."),
]
ai_msg = llm.invoke(messages)
ai_msg

AIMessage(content="J'adore la programmation.", response_metadata={'id': 'msg_018Nnu76krRPq8HvgKLW4F8T', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 29, 'output_tokens': 11}}, id='run-57e9295f-db8a-48dc-9619-babd2bedd891-0', usage_metadata={'input_tokens': 29, 'output_tokens': 11, 'total_tokens': 40})

print(ai_msg.content)

J'adore la programmation.

链式调用

我们可以像这样将我们的模型与提示模板链接：

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a helpful assistant that translates {input_language} to {output_language}.",
        ),
        ("human", "{input}"),
    ]
)

chain = prompt | llm
chain.invoke(
    {
        "input_language": "English",
        "output_language": "German",
        "input": "I love programming.",
    }
)

API 参考：ChatPromptTemplate

AIMessage(content="Here's the German translation:\n\nIch liebe Programmieren.", response_metadata={'id': 'msg_01GhkRtQZUkA5Ge9hqmD8HGY', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 23, 'output_tokens': 18}}, id='run-da5906b4-b200-4e08-b81a-64d4453643b6-0', usage_metadata={'input_tokens': 23, 'output_tokens': 18, 'total_tokens': 41})

内容块

来自单个Anthropic AI消息的内容可以是单个字符串，也可以是内容块列表。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 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")


llm_with_tools = llm.bind_tools([GetWeather])
ai_msg = llm_with_tools.invoke("Which city is hotter today: LA or NY?")
ai_msg.content

[{'text': "To answer this question, we'll need to check the current weather in both Los Angeles (LA) and New York (NY). I'll use the GetWeather function to retrieve this information for both cities.",
  'type': 'text'},
 {'id': 'toolu_01Ddzj5PkuZkrjF4tafzu54A',
  'input': {'location': 'Los Angeles, CA'},
  'name': 'GetWeather',
  'type': 'tool_use'},
 {'id': 'toolu_012kz4qHZQqD4qg8sFPeKqpP',
  'input': {'location': 'New York, NY'},
  'name': 'GetWeather',
  'type': 'tool_use'}]

ai_msg.tool_calls

[{'name': 'GetWeather',
  'args': {'location': 'Los Angeles, CA'},
  'id': 'toolu_01Ddzj5PkuZkrjF4tafzu54A'},
 {'name': 'GetWeather',
  'args': {'location': 'New York, NY'},
  'id': 'toolu_012kz4qHZQqD4qg8sFPeKqpP'}]

扩展思考

Claude 3.7 Sonnet 支持扩展思考功能，该功能将输出导致其最终答案的逐步推理过程。

要使用它，请在初始化 ChatAnthropic 时指定 thinking 参数。它也可以在调用期间作为关键字参数传入。

你需要指定一个令牌预算来使用此功能。请参阅下面的使用示例：

import json

from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(
    model="claude-3-7-sonnet-latest",
    max_tokens=5000,
    thinking={"type": "enabled", "budget_tokens": 2000},
)

response = llm.invoke("What is the cube root of 50.653?")
print(json.dumps(response.content, indent=2))

API 参考：ChatAnthropic

[
  {
    "signature": "ErUBCkYIARgCIkCx7bIPj35jGPHpoVOB2y5hvPF8MN4lVK75CYGftmVNlI4axz2+bBbSexofWsN1O/prwNv8yPXnIXQmwT6zrJsKEgwJzvks0yVRZtaGBScaDOm9xcpOxbuhku1zViIw9WDgil/KZL8DsqWrhVpC6TzM0RQNCcsHcmgmyxbgG9g8PR0eJGLxCcGoEw8zMQu1Kh1hQ1/03hZ2JCOgigpByR9aNPTwwpl64fQUe6WwIw==",
    "thinking": "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.",
    "type": "thinking"
  },
  {
    "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.",
    "type": "text"
  }
]

提示缓存

Anthropic 支持对提示的部分内容进行缓存，包括消息、工具定义、工具结果、图像和文档。这使您可以重复使用大型文档、指令、少量示例文档以及其他数据，从而减少延迟并降低成本。

要对提示的某个元素启用缓存，请使用 cache_control 键标记其关联的内容块。请参见以下示例：

消息

import requests
from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(model="claude-3-7-sonnet-20250219")

# 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 = llm.invoke(messages)
response_2 = llm.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}")

API 参考：ChatAnthropic

First invocation:
{'cache_read': 0, 'cache_creation': 1458}

Second:
{'cache_read': 1458, 'cache_creation': 0}

工具

from langchain_anthropic import convert_to_anthropic_tool
from langchain_core.tools import tool

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


@tool(description=description)
def get_weather(location: str) -> str:
    return "It's sunny."


# Enable caching on the tool
weather_tool = convert_to_anthropic_tool(get_weather)
weather_tool["cache_control"] = {"type": "ephemeral"}

llm = ChatAnthropic(model="claude-3-7-sonnet-20250219")
llm_with_tools = llm.bind_tools([weather_tool])
query = "What's the weather in San Francisco?"

response_1 = llm_with_tools.invoke(query)
response_2 = llm_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}")

API 参考：convert_to_anthropic_tool | 工具

First invocation:
{'cache_read': 0, 'cache_creation': 1809}

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

对话式应用中的增量缓存

提示缓存可以用于多轮对话中，以在不进行冗余处理的情况下保留早期消息的上下文。

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 将自动为后续消息使用最长的先前缓存前缀。

下面，我们实现了一个包含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缩减器，它会自动将每个用户消息中的最后一个内容块标记为cache_control。请参见下文：

import requests
from langchain_anthropic import ChatAnthropic
from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import START, StateGraph, add_messages
from typing_extensions import Annotated, TypedDict

llm = ChatAnthropic(model="claude-3-7-sonnet-20250219")

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


def messages_reducer(left: list, right: list) -> list:
    # Update last user message
    for i in range(len(right) - 1, -1, -1):
        if right[i].type == "human":
            right[i].content[-1]["cache_control"] = {"type": "ephemeral"}
            break

    return add_messages(left, right)


class State(TypedDict):
    messages: Annotated[list, messages_reducer]


workflow = StateGraph(state_schema=State)


# Define the function that calls the model
def call_model(state: State):
    response = llm.invoke(state["messages"])
    return {"messages": [response]}


# Define the (single) node in the graph
workflow.add_edge(START, "model")
workflow.add_node("model", call_model)

# Add memory
memory = MemorySaver()
app = workflow.compile(checkpointer=memory)

API 参考：ChatAnthropic | MemorySaver | StateGraph | add_messages

from langchain_core.messages import HumanMessage

config = {"configurable": {"thread_id": "abc123"}}

query = "Hi! I'm Bob."

input_message = HumanMessage([{"type": "text", "text": query}])
output = app.invoke({"messages": [input_message]}, config)
output["messages"][-1].pretty_print()
print(f'\n{output["messages"][-1].usage_metadata["input_token_details"]}')

API 参考：HumanMessage

================================== Ai Message ==================================

Hello, Bob! It's nice to meet you. How are you doing today? Is there something I can help you with?

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

query = f"Check out this readme: {readme}"

input_message = HumanMessage([{"type": "text", "text": query}])
output = app.invoke({"messages": [input_message]}, config)
output["messages"][-1].pretty_print()
print(f'\n{output["messages"][-1].usage_metadata["input_token_details"]}')

================================== Ai Message ==================================

I can see you've shared the README from the LangChain GitHub repository. This is the documentation for LangChain, which is a popular framework for building applications powered by Large Language Models (LLMs). Here's a summary of what the README contains:

LangChain is:
- A framework for developing LLM-powered applications
- Helps chain together components and integrations to simplify AI application development
- Provides a standard interface for models, embeddings, vector stores, etc.

Key features/benefits:
- Real-time data augmentation (connect LLMs to diverse data sources)
- Model interoperability (swap models easily as needed)
- Large ecosystem of integrations

The LangChain ecosystem includes:
- LangSmith - For evaluations and observability
- LangGraph - For building complex agents with customizable architecture
- LangGraph Platform - For deployment and scaling of agents

The README also mentions installation instructions (`pip install -U langchain`) and links to various resources including tutorials, how-to guides, conceptual guides, and API references.

Is there anything specific about LangChain you'd like to know more about, Bob?

{'cache_read': 0, 'cache_creation': 1498}

query = "What was my name again?"

input_message = HumanMessage([{"type": "text", "text": query}])
output = app.invoke({"messages": [input_message]}, config)
output["messages"][-1].pretty_print()
print(f'\n{output["messages"][-1].usage_metadata["input_token_details"]}')

================================== Ai Message ==================================

Your name is Bob. You introduced yourself at the beginning of our conversation.

{'cache_read': 1498, 'cache_creation': 269}

在 LangSmith 跟踪 中，切换“原始输出”将准确显示发送到聊天模型的消息，包括 cache_control 键。

高效的工具使用令牌

Anthropic 支持（测试版）高效令牌使用工具功能。要使用它，请在实例化模型时指定相关的 beta-headers。

from langchain_anthropic import ChatAnthropic
from langchain_core.tools import tool

llm = ChatAnthropic(
    model="claude-3-7-sonnet-20250219",
    temperature=0,
    model_kwargs={
        "extra_headers": {"anthropic-beta": "token-efficient-tools-2025-02-19"}
    },
)


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


llm_with_tools = llm.bind_tools([get_weather])
response = llm_with_tools.invoke("What's the weather in San Francisco?")
print(response.tool_calls)
print(f'\nTotal tokens: {response.usage_metadata["total_tokens"]}')

API 参考：ChatAnthropic | 工具

[{'name': 'get_weather', 'args': {'location': 'San Francisco'}, 'id': 'toolu_01EoeE1qYaePcmNbUvMsWtmA', 'type': 'tool_call'}]

Total tokens: 408

引用

Anthropic 支持一种引用功能，该功能允许 Claude 根据用户提供的源文档为其答案附加上下文。当查询中包含带有"citations": {"enabled": True}的文档内容块时，Claude 可能在其回复中生成引用。

简单示例

在此示例中，我们传递了一个纯文本文档。在后台，Claude会自动将输入文本分割成句子，这些句子在生成引用时会被使用。

from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(model="claude-3-5-haiku-latest")

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 = llm.invoke(messages)
response.content

API 参考：ChatAnthropic

[{'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'}]

与文本分割器一起使用

Anthropic 还允许您通过使用 自定义文档 类型来指定自己的分块方式。LangChain 的 文本分块器 可用于生成有意义的分块，以实现此目的。请参见下面的示例，我们将 LangChain 的 README（一个 Markdown 文档）进行分块，并将其作为上下文传递给 Claude：

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 LLM
llm = ChatAnthropic(model="claude-3-5-haiku-latest")
response = llm.invoke([message])

response.content

API 参考：ChatAnthropic | MarkdownTextSplitter

[{'text': "You can find LangChain's tutorials at https://python.langchain.com/docs/tutorials/\n\nThe tutorials section is recommended for those looking to build something specific or who prefer a hands-on learning approach. It's considered the best place to get started with LangChain.",
  'type': 'text',
  'citations': [{'type': 'content_block_location',
    'cited_text': "[Tutorials](https://python.langchain.com/docs/tutorials/):If you're looking to build something specific orare more of a hands-on learner, check out ourtutorials. This is the best place to get started.",
    'document_index': 0,
    'document_title': None,
    'start_block_index': 243,
    'end_block_index': 248}]}]

内置工具

Anthropic 支持多种 内置工具，这些工具可以按照 常规方式 绑定到模型。Claude 将根据其内部工具架构生成工具调用：

网络搜索

Claude 可以使用 网络搜索工具 来运行搜索，并通过引用为其回答提供依据。

from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(model="claude-3-5-sonnet-latest")

tool = {"type": "web_search_20250305", "name": "web_search", "max_uses": 3}
llm_with_tools = llm.bind_tools([tool])

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

API 参考：ChatAnthropic

文本编辑器

文本编辑器工具可用于查看和修改文本文件。详情请参阅此处的文档。

from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(model="claude-3-7-sonnet-20250219")

tool = {"type": "text_editor_20250124", "name": "str_replace_editor"}
llm_with_tools = llm.bind_tools([tool])

response = llm_with_tools.invoke(
    "There's a syntax error in my primes.py file. Can you help me fix it?"
)
print(response.text())
response.tool_calls

API 参考：ChatAnthropic

I'd be happy to help you fix the syntax error in your primes.py file. First, let's look at the current content of the file to identify the error.

[{'name': 'str_replace_editor',
  'args': {'command': 'view', 'path': '/repo/primes.py'},
  'id': 'toolu_01VdNgt1YV7kGfj9LFLm6HyQ',
  'type': 'tool_call'}]

API 参考

有关ChatAnthropic所有功能和配置的详细文档，请访问API参考： https://python.langchain.com/api_reference/anthropic/chat_models/langchain_anthropic.chat_models.ChatAnthropic.html

相关

• 聊天模型 概念指南
• 聊天模型 操操作指南