Skip to main content
LangChain 实现了一个流式系统，用于展示实时更新。 流式传输对于增强基于大语言模型（LLM）构建的应用程序的响应性至关重要。通过逐步显示输出，甚至在完整响应准备好之前，流式传输显著改善了用户体验（UX），特别是在处理 LLM 的延迟时。

​
概述

LangChain 的流式系统允许您将智能体运行的实时反馈展示到您的应用程序中。 使用 LangChain 流式传输可以实现： 请参阅下面的 常见模式 部分以获取更多端到端示例。

​
支持的流模式

将以下一个或多个流模式作为列表传递给 stream 方法：
模式描述
updates在每个智能体步骤后流式传输状态更新。如果同一步骤中有多个更新（例如，运行了多个节点），这些更新将分别流式传输。
messages流式传输来自任何调用 LLM 的图节点的 (token, metadata) 元组。
custom使用流写入器从您的图节点内部流式传输自定义数据。

​
智能体进度

要流式传输智能体进度，请使用 stream 方法并设置 streamMode: "updates"。这会在每个智能体步骤后发射一个事件。 例如，如果您有一个调用一次工具的代理，您应该看到以下更新：
  • LLM 节点：带有工具调用请求的 AIMessage
  • 工具节点：带有执行结果的 ToolMessage
  • LLM 节点：最终 AI 响应
import z from "zod";
import { createAgent, tool } from "langchain";

const getWeather = tool(
    async ({ city }) => {
        return `The weather in ${city} is always sunny!`;
    },
    {
        name: "get_weather",
        description: "Get weather for a given city.",
        schema: z.object({
        city: z.string(),
        }),
    }
);

const agent = createAgent({
    model: "gpt-5-nano",
    tools: [getWeather],
});

for await (const chunk of await agent.stream(
    { messages: [{ role: "user", content: "what is the weather in sf" }] },
    { streamMode: "updates" }
)) {
    const [step, content] = Object.entries(chunk)[0];
    console.log(`step: ${step}`);
    console.log(`content: ${JSON.stringify(content, null, 2)}`);
}
/**
 * step: model
 * content: {
 *   "messages": [
 *     {
 *       "kwargs": {
 *         // ...
 *         "tool_calls": [
 *           {
 *             "name": "get_weather",
 *             "args": {
 *               "city": "San Francisco"
 *             },
 *             "type": "tool_call",
 *             "id": "call_0qLS2Jp3MCmaKJ5MAYtr4jJd"
 *           }
 *         ],
 *         // ...
 *       }
 *     }
 *   ]
 * }
 * step: tools
 * content: {
 *   "messages": [
 *     {
 *       "kwargs": {
 *         "content": "The weather in San Francisco is always sunny!",
 *         "name": "get_weather",
 *         // ...
 *       }
 *     }
 *   ]
 * }
 * step: model
 * content: {
 *   "messages": [
 *     {
 *       "kwargs": {
 *         "content": "The latest update says: The weather in San Francisco is always sunny!\n\nIf you'd like real-time details (current temperature, humidity, wind, and today's forecast), I can pull the latest data for you. Want me to fetch that?",
 *         // ...
 *       }
 *     }
 *   ]
 * }
 */

​
LLM 令牌

要流式传输由 LLM 产生的令牌，请使用 streamMode: "messages"： 
import z from "zod";
import { createAgent, tool } from "langchain";

const getWeather = tool(
    async ({ city }) => {
        return `The weather in ${city} is always sunny!`;
    },
    {
        name: "get_weather",
        description: "Get weather for a given city.",
        schema: z.object({
        city: z.string(),
        }),
    }
);

const agent = createAgent({
    model: "gpt-4.1-mini",
    tools: [getWeather],
});

for await (const [token, metadata] of await agent.stream(
    { messages: [{ role: "user", content: "what is the weather in sf" }] },
    { streamMode: "messages" }
)) {
    console.log(`node: ${metadata.langgraph_node}`);
    console.log(`content: ${JSON.stringify(token.contentBlocks, null, 2)}`);
}

​
自定义更新

要流式传输工具执行时的更新，您可以使用配置中的 writer 参数。 
import z from "zod";
import { tool, createAgent } from "langchain";
import { LangGraphRunnableConfig } from "@langchain/langgraph";

const getWeather = tool(
    async (input, config: LangGraphRunnableConfig) => {
        // Stream any arbitrary data
        config.writer?.(`Looking up data for city: ${input.city}`);
        // ... fetch city data
        config.writer?.(`Acquired data for city: ${input.city}`);
        return `It's always sunny in ${input.city}!`;
    },
    {
        name: "get_weather",
        description: "Get weather for a given city.",
        schema: z.object({
        city: z.string().describe("The city to get weather for."),
        }),
    }
);

const agent = createAgent({
    model: "gpt-4.1-mini",
    tools: [getWeather],
});

for await (const chunk of await agent.stream(
    { messages: [{ role: "user", content: "what is the weather in sf" }] },
    { streamMode: "custom" }
)) {
    console.log(chunk);
}
Output
Looking up data for city: San Francisco
Acquired data for city: San Francisco
如果您将 writer 参数添加到工具中，您将无法在没有提供 writer 函数的情况下在 LangGraph 执行上下文之外调用该工具。

​
流式传输多种模式

您可以通过传递流模式数组来指定多个流模式：streamMode: ["updates", "messages", "custom"]。 流式传输的输出将是 [mode, chunk] 元组，其中 mode 是流模式的名称，chunk 是该模式流式传输的数据。 
import z from "zod";
import { tool, createAgent } from "langchain";
import { LangGraphRunnableConfig } from "@langchain/langgraph";

const getWeather = tool(
    async (input, config: LangGraphRunnableConfig) => {
        // Stream any arbitrary data
        config.writer?.(`Looking up data for city: ${input.city}`);
        // ... fetch city data
        config.writer?.(`Acquired data for city: ${input.city}`);
        return `It's always sunny in ${input.city}!`;
    },
    {
        name: "get_weather",
        description: "Get weather for a given city.",
        schema: z.object({
        city: z.string().describe("The city to get weather for."),
        }),
    }
);

const agent = createAgent({
    model: "gpt-4.1-mini",
    tools: [getWeather],
});

for await (const [streamMode, chunk] of await agent.stream(
    { messages: [{ role: "user", content: "what is the weather in sf" }] },
    { streamMode: ["updates", "messages", "custom"] }
)) {
    console.log(`${streamMode}: ${JSON.stringify(chunk, null, 2)}`);
}

​
常见模式

以下是展示流式传输常见用例的示例。

​
流式传输思考/推理令牌

某些模型在生成最终答案之前会进行内部推理。您可以通过过滤 标准内容块 的 type 为 "reasoning" 来流式传输这些正在生成的思考/推理令牌。
必须在模型上启用推理输出。请参阅 推理部分 和您的 提供商的集成页面 以获取配置详情。要快速检查模型的推理支持情况，请查看 models.dev。
要从智能体流式传输思考令牌，请使用 streamMode: "messages" 并过滤推理内容块。当模型支持时，使用具有扩展思考功能的模型实例（例如 ChatAnthropic）： 
import z from "zod";
import { createAgent, tool } from "langchain";
import { ChatAnthropic } from "@langchain/anthropic";

const getWeather = tool(
  async ({ city }) => {
    return `It's always sunny in ${city}!`;
  },
  {
    name: "get_weather",
    description: "Get weather for a given city.",
    schema: z.object({ city: z.string() }),
  },
);

const agent = createAgent({
  model: new ChatAnthropic({
    model: "claude-sonnet-4-6",
    thinking: { type: "enabled", budget_tokens: 5000 },
  }),
  tools: [getWeather],
});

for await (const [token, metadata] of await agent.stream(
  { messages: [{ role: "user", content: "What is the weather in SF?" }] },
  { streamMode: "messages" },
)) {
  if (!token.contentBlocks) continue;
  const reasoning = token.contentBlocks.filter((b) => b.type === "reasoning");
  const text = token.contentBlocks.filter((b) => b.type === "text");
  if (reasoning.length) {
    process.stdout.write(`[thinking] ${reasoning[0].reasoning}`);
  }
  if (text.length) {
    process.stdout.write(text[0].text);
  }
}
Output
[thinking] The user is asking about the weather in San Francisco. I have a tool
[thinking]  available to get this information. Let me call the get_weather tool
[thinking]  with "San Francisco" as the city parameter.
The weather in San Francisco is: It's always sunny in San Francisco!
无论模型提供商如何，其工作原理相同—LangChain 将特定于提供商的格式（Anthropic thinking 块、OpenAI reasoning 摘要等）通过 content_blocks 属性标准化为标准的 "reasoning" 内容块类型。 要从聊天模型直接流式传输推理令牌（不使用智能体），请参阅 与聊天模型流式传输。

​
禁用流式传输

在某些应用程序中，您可能需要禁用给定模型的单个令牌的流式传输。这在以下情况下很有用：
  • 与 多智能体 系统一起工作以控制哪些智能体流式传输其输出
  • 混合支持流式传输和不支持流式传输的模型
  • 部署到 LangSmith 并希望防止某些模型输出流式传输到客户端
初始化模型时设置 streaming: false。 
import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  model: "gpt-4.1",
  streaming: false,
});
部署到 LangSmith 时，对任何您不希望流式传输到客户端的模型设置 streaming=False。这是在部署前在您的图代码中配置的。
并非所有聊天模型集成都支持 streaming 参数。如果您的模型不支持它，请使用 disableStreaming: true。此参数通过基类在所有聊天模型上可用。
有关更多详细信息，请参阅 LangGraph 流式指南。

​
相关资源

Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.