> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# LangChain v1 更新了什么

**LangChain v1 是一个专注于构建智能体的、面向生产环境的基础框架。** 我们围绕三项核心改进简化了该框架：

<CardGroup cols={1}>
  <Card title="create_agent" icon="robot" href="#create-agent" arrow>
    LangChain 中构建智能体的新标准，替代 `langgraph.prebuilt.create_react_agent`。
  </Card>

  <Card title="Standard content blocks" icon="cube" href="#standard-content-blocks" arrow>
    新的 `content_blocks` 属性，提供跨提供商的现代 LLM 功能的统一访问。
  </Card>

  <Card title="Simplified namespace" icon="sitemap" href="#simplified-package" arrow>
    `langchain` 命名空间已简化，专注于智能体的基本构建块，遗留功能已移至 `langchain-classic`。
  </Card>
</CardGroup>

要升级，

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install -U langchain
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add langchain
  ```
</CodeGroup>

有关更改的完整列表，请参阅 [迁移指南](/oss/python/migrate/langchain-v1)。

## `create_agent`

[`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) 是 LangChain 1.0 中构建智能体的标准方式。它提供了比 [`langgraph.prebuilt.create_react_agent`](https://reference.langchain.com/python/langchain-classic/agents/react/agent/create_react_agent) 更简单的接口，同时通过使用 [middleware](#middleware) 提供了更大的自定义潜力。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain.agents import create_agent

agent = create_agent(
    model="claude-sonnet-4-6",
    tools=[search_web, analyze_data, send_email],
    system_prompt="You are a helpful research assistant."
)

result = agent.invoke({
    "messages": [
        {"role": "user", "content": "Research AI safety trends"}
    ]
})
```

在底层，[`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) 基于基本的智能体循环构建——调用模型，让它选择要执行的工具，然后在它不再调用任何工具时结束：

<div style={{ display: "flex", justifyContent: "center" }}>
  <img src="https://mintcdn.com/hhh-8c10bf0c/jRI9Uh24bT9O5tSI/oss/images/core_agent_loop.png?fit=max&auto=format&n=jRI9Uh24bT9O5tSI&q=85&s=92d697bbbf0448295354920392c65af9" alt="核心智能体循环图" className="rounded-lg" width="300" height="268" data-path="oss/images/core_agent_loop.png" />
</div>

更多信息，请参见 [Agents](/oss/python/langchain/agents)。

### Middleware

Middleware 是 [`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) 的定义特性。它提供了一个高度可定制的入口点，提高了您能构建内容的上限。

优秀的智能体需要 [上下文工程](/oss/python/langchain/context-engineering)：在正确的时间将正确的信息传递给模型。Middleware 帮助您通过可组合的抽象控制动态提示、对话摘要、选择性工具访问、状态管理和护栏。

#### Prebuilt middleware

LangChain 为常见模式提供了一些 [预构建中间件](/oss/python/langchain/middleware#built-in-middleware)，包括：

* [`PIIMiddleware`](https://reference.langchain.com/python/langchain/agents/middleware/pii/PIIMiddleware)：在发送给模型之前删除敏感信息
* [`SummarizationMiddleware`](https://reference.langchain.com/python/langchain/agents/middleware/summarization/SummarizationMiddleware)：当对话历史过长时压缩它
* [`HumanInTheLoopMiddleware`](https://reference.langchain.com/python/langchain/agents/middleware/human_in_the_loop/HumanInTheLoopMiddleware)：对敏感工具调用要求批准

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain.agents import create_agent
from langchain.agents.middleware import (
    PIIMiddleware,
    SummarizationMiddleware,
    HumanInTheLoopMiddleware
)


agent = create_agent(
    model="claude-sonnet-4-6",
    tools=[read_email, send_email],
    middleware=[
        PIIMiddleware("email", strategy="redact", apply_to_input=True),
        PIIMiddleware(
            "phone_number",
            detector=(
                r"(?:\+?\d{1,3}[\s.-]?)?"
                r"(?:\(?\d{2,4}\)?[\s.-]?)?"
                r"\d{3,4}[\s.-]?\d{4}"
			),
			strategy="block"
        ),
        SummarizationMiddleware(
            model="claude-sonnet-4-6",
            trigger={"tokens": 500}
        ),
        HumanInTheLoopMiddleware(
            interrupt_on={
                "send_email": {
                    "allowed_decisions": ["approve", "edit", "reject"]
                }
            }
        ),
    ]
)
```

#### Custom middleware

您也可以构建自定义中间件以满足您的需求。中间件在智能体执行的每一步都暴露钩子：

<div style={{ display: "flex", justifyContent: "center" }}>
  <img src="https://mintcdn.com/hhh-8c10bf0c/nuzu1mnzaCcJfRiZ/oss/images/middleware_final.png?fit=max&auto=format&n=nuzu1mnzaCcJfRiZ&q=85&s=30e8729fd3bce0b5c6f9195910e80620" alt="中间件流程图" className="rounded-lg" width="500" height="560" data-path="oss/images/middleware_final.png" />
</div>

通过在 [`AgentMiddleware`](https://reference.langchain.com/python/langchain/agents/middleware/types/AgentMiddleware) 类的子类上实现以下任何钩子来构建自定义中间件：

| Hook              | When it runs             | Use cases                               |
| ----------------- | ------------------------ | --------------------------------------- |
| `before_agent`    | Before calling the agent | Load memory, validate input             |
| `before_model`    | Before each LLM call     | Update prompts, trim messages           |
| `wrap_model_call` | Around each LLM call     | Intercept and modify requests/responses |
| `wrap_tool_call`  | Around each tool call    | Intercept and modify tool execution     |
| `after_model`     | After each LLM response  | Validate output, apply guardrails       |
| `after_agent`     | After agent completes    | Save results, cleanup                   |

示例自定义中间件：

```python expandable theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from dataclasses import dataclass
from typing import Callable

from langchain_openai import ChatOpenAI

from langchain.agents.middleware import (
    AgentMiddleware,
    ModelRequest
)
from langchain.agents.middleware.types import ModelResponse

@dataclass
class Context:
    user_expertise: str = "beginner"

class ExpertiseBasedToolMiddleware(AgentMiddleware):
    def wrap_model_call(
        self,
        request: ModelRequest,
        handler: Callable[[ModelRequest], ModelResponse]
    ) -> ModelResponse:
        user_level = request.runtime.context.user_expertise

        if user_level == "expert":
            # More powerful model
            model = ChatOpenAI(model="gpt-5")
            tools = [advanced_search, data_analysis]
        else:
            # Less powerful model
            model = ChatOpenAI(model="gpt-5-nano")
            tools = [simple_search, basic_calculator]

        return handler(request.override(model=model, tools=tools))

agent = create_agent(
    model="claude-sonnet-4-6",
    tools=[
        simple_search,
        advanced_search,
        basic_calculator,
        data_analysis
    ],
    middleware=[ExpertiseBasedToolMiddleware()],
    context_schema=Context
)
```

更多信息，请参见 [完整的中间件指南](/oss/python/langchain/middleware)。

### Built on LangGraph

因为 [`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) 是基于 [LangGraph](/oss/python/langgraph) 构建的，所以您自动获得了对长运行和可靠智能体的内置支持，通过：

<CardGroup cols={2}>
  <Card title="Persistence" icon="database">
    会话在跨会话时自动持久化，具有内置的检查点功能
  </Card>

  <Card title="Streaming" icon="droplet">
    实时流式传输令牌、工具调用和推理轨迹
  </Card>

  <Card title="Human-in-the-loop" icon="hand-stop">
    暂停智能体执行以在敏感操作前获得人类批准
  </Card>

  <Card title="Time travel" icon="history">
    将对话回退到任何时间点并探索替代路径和提示
  </Card>
</CardGroup>

您不需要学习 LangGraph 即可使用这些功能——它们开箱即用。

### Structured output

[`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) 改进了结构化输出生成：

* **Main loop integration**：结构化输出现在在主循环中生成，而不是需要额外的 LLM 调用
* **Structured output strategy**：模型可以选择调用工具或使用提供商侧的结构化输出生成
* **Cost reduction**：消除了额外 LLM 调用的额外费用

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy
from pydantic import BaseModel


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

def weather_tool(city: str) -> str:
    """Get the weather for a city."""
    return f"it's sunny and 70 degrees in {city}"

agent = create_agent(
    "gpt-4.1-mini",
    tools=[weather_tool],
    response_format=ToolStrategy(Weather)
)

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

print(repr(result["structured_response"]))
# results in `Weather(temperature=70.0, condition='sunny')`
```

**错误处理**：通过 `ToolStrategy` 的 `handle_errors` 参数控制错误处理：

* **Parsing errors**：模型生成的数据与所需结构不匹配
* **Multiple tool calls**：模型为结构化输出架构生成了 2 个或更多工具调用

***

## Standard content blocks

<Note>
  内容块支持目前仅适用于以下集成：

  * [`langchain-anthropic`](https://pypi.org/project/langchain-anthropic/)
  * [`langchain-aws`](https://pypi.org/project/langchain-aws/)
  * [`langchain-openai`](https://pypi.org/project/langchain-openai/)
  * [`langchain-google-genai`](https://pypi.org/project/langchain-google-genai/)
  * [`langchain-ollama`](https://pypi.org/project/langchain-ollama/)

  更广泛的内容块支持将逐渐扩展到更多提供商。
</Note>

新的 [`content_blocks`](https://reference.langchain.com/python/langchain-core/messages/base/BaseMessage) 属性引入了跨提供商工作的消息内容的标准表示形式：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-sonnet-4-6")
response = model.invoke("What's the capital of France?")

# Unified access to content blocks
for block in response.content_blocks:
    if block["type"] == "reasoning":
        print(f"Model reasoning: {block['reasoning']}")
    elif block["type"] == "text":
        print(f"Response: {block['text']}")
    elif block["type"] == "tool_call":
        print(f"Tool call: {block['name']}({block['args']})")
```

### Benefits

* **Provider agnostic**：无论提供商如何，使用相同的 API 访问推理轨迹、引用、内置工具（网络搜索、代码解释器等）和其他功能
* **Type safe**：所有内容块类型的完整类型提示
* **Backward compatible**：标准内容可以 [延迟加载](/oss/python/langchain/messages#standard-content-blocks)，因此没有相关的破坏性更改

更多信息，请参见我们的 [内容块指南](/oss/python/langchain/messages#standard-content-blocks)。

***

## Simplified package

LangChain v1 简化了 [`langchain`](https://pypi.org/project/langchain/) 包命名空间，专注于智能体的基本构建块。精简后的命名空间暴露了最有用和最相关的功能：

### Namespace

| Module                                                                                | What's available                                                                                                                                                                                                            | Notes                                                                                       |
| ------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- |
| [`langchain.agents`](https://reference.langchain.com/python/langchain/agents)         | [`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent), [`AgentState`](https://reference.langchain.com/python/langchain/agents/middleware/types/AgentState)                         | Core agent creation functionality                                                           |
| [`langchain.messages`](https://reference.langchain.com/python/langchain/messages)     | Message types, [content blocks](https://reference.langchain.com/python/langchain-core/messages/content/ContentBlock), [`trim_messages`](https://reference.langchain.com/python/langchain-core/messages/utils/trim_messages) | Re-exported from [`langchain-core`](https://reference.langchain.com/python/langchain-core/) |
| [`langchain.tools`](https://reference.langchain.com/python/langchain/tools)           | [`@tool`](https://reference.langchain.com/python/langchain-core/tools/convert/tool), [`BaseTool`](https://reference.langchain.com/python/langchain-core/tools/base/BaseTool), injection helpers                             | Re-exported from [`langchain-core`](https://reference.langchain.com/python/langchain-core/) |
| [`langchain.chat_models`](https://reference.langchain.com/python/langchain/models)    | [`init_chat_model`](https://reference.langchain.com/python/langchain/chat_models/base/init_chat_model), [`BaseChatModel`](https://reference.langchain.com/python/langchain-core/language_models/chat_models/BaseChatModel)  | Unified model initialization                                                                |
| [`langchain.embeddings`](https://reference.langchain.com/python/langchain/embeddings) | [`Embeddings`](https://reference.langchain.com/python/langchain-core/embeddings/embeddings/Embeddings), [`init_embeddings`](https://reference.langchain.com/python/langchain/embeddings/base/init_embeddings)               | Embedding models                                                                            |

其中大多数是从 `langchain-core` 重新导出的，以便为您提供用于构建智能体的聚焦 API 表面。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Agent building
from langchain.agents import create_agent

# Messages and content
from langchain.messages import AIMessage, HumanMessage

# Tools
from langchain.tools import tool

# Model initialization
from langchain.chat_models import init_chat_model
from langchain.embeddings import init_embeddings
```

### `langchain-classic`

遗留功能已移至 [`langchain-classic`](https://pypi.org/project/langchain-classic)，以保持核心包精简且专注。

**`langchain-classic` 中包含：**

* Legacy chains and chain implementations
* Retrievers (e.g. `MultiQueryRetriever` or anything from the previous `langchain.retrievers` module)
* The indexing API
* The hub module (for managing prompts programmatically)
* [`langchain-community`](https://pypi.org/project/langchain-community) exports
* Other deprecated functionality

如果您使用此功能中的任何一项，请安装 [`langchain-classic`](https://pypi.org/project/langchain-classic)：

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install langchain-classic
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add langchain-classic
  ```
</CodeGroup>

然后更新您的导入：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain import ...  # [!code --]
from langchain_classic import ...  # [!code ++]

from langchain.chains import ...  # [!code --]
from langchain_classic.chains import ...  # [!code ++]

from langchain.retrievers import ...  # [!code --]
from langchain_classic.retrievers import ...  # [!code ++]

from langchain import hub  # [!code --]
from langchain_classic import hub  # [!code ++]
```

## Migration guide

查看我们的 [迁移指南](/oss/python/migrate/langchain-v1) 以帮助将代码更新为 LangChain v1。

## Reporting issues

请在 [GitHub](https://github.com/langchain-ai/langchain/issues) 上报告发现的任何 1.0 问题，并使用 `'v1'` [标签](https://github.com/langchain-ai/langchain/issues?q=state%3Aopen%20label%3Av1)。

## Additional resources

<CardGroup cols={3}>
  <Card title="LangChain 1.0" icon="rocket" href="https://blog.langchain.com/langchain-langchain-1-0-alpha-releases/">
    阅读公告
  </Card>

  <Card title="Middleware guide" icon="puzzle" href="https://blog.langchain.com/agent-middleware/">
    深入探讨中间件
  </Card>

  <Card title="Agents Documentation" icon="book" href="/oss/python/langchain/agents" arrow>
    完整的智能体文档
  </Card>

  <Card title="Message Content" icon="message" href="/oss/python/langchain/messages#message-content" arrow>
    新的内容块 API
  </Card>

  <Card title="Migration guide" icon="arrows-exchange" href="/oss/python/migrate/langchain-v1" arrow>
    如何迁移到 LangChain v1
  </Card>

  <Card title="GitHub" icon="brand-github" href="https://github.com/langchain-ai/langchain">
    报告问题或贡献
  </Card>
</CardGroup>

## See also

* [Versioning](/oss/python/versioning) – Understanding version numbers
* [Release policy](/oss/python/release-policy) – Detailed release policies

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\python\releases\langchain-v1.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>