Skip to main content
结构化输出允许代理以特定的、可预测的格式返回数据。您无需解析自然语言响应，而是获取类型化的结构化数据。 LangChain 预构建的 ReAct 代理 createAgent 自动处理结构化输出。用户设置他们期望的结构化输出模式，当模型生成结构化数据时，它会被捕获、验证并返回到代理状态的 structuredResponse 键中。 
type ResponseFormat = (
    | ZodSchema<StructuredResponseT> // a Zod schema
    | Record<string, unknown> // a JSON Schema
)

const agent = createAgent({
    // ...
    responseFormat: ResponseFormat | ResponseFormat[]
})

​
响应格式

控制代理如何返回结构化数据。您可以提供 Zod 对象或 JSON 模式。默认情况下，代理使用工具调用策略，其中输出通过额外的工具调用创建。某些模型支持原生结构化输出，在这种情况下，代理将改用该策略。 您可以通过将 ResponseFormat 包装在 toolStrategy 或 providerStrategy 函数调用中来控制此行为： 
import { toolStrategy, providerStrategy } from "langchain";

const agent = createAgent({
    // use a provider strategy if supported by the model
    responseFormat: providerStrategy(z.object({ ... }))
    // or enforce a tool strategy
    responseFormat: toolStrategy(z.object({ ... }))
})
结构化响应在代理最终状态的 structuredResponse 键中返回。

​
提供商策略

一些模型提供商通过其 API 原生支持结构化输出（目前仅 OpenAI 和 Grok）。当可用时，这是最可靠的方法。 要使用此策略，请配置一个 ProviderStrategy： 
function providerStrategy<StructuredResponseT>(
    schema: ZodSchema<StructuredResponseT> | JsonSchemaFormat
): ProviderStrategy<StructuredResponseT>
​
schema
required
定义结构化输出格式的模式。支持：
  • Zod 模式：一个 zod 模式
  • JSON 模式：一个 JSON 模式对象
当您将模式类型直接传递给 createAgent.responseFormat 并且模型支持原生结构化输出时，LangChain 会自动使用 ProviderStrategy： 
import * as z from "zod";
import { createAgent, providerStrategy } from "langchain";

const ContactInfo = z.object({
    name: z.string().describe("The name of the person"),
    email: z.string().describe("The email address of the person"),
    phone: z.string().describe("The phone number of the person"),
});

const agent = createAgent({
    model: "openai:gpt-5",
    tools: tools,
    responseFormat: providerStrategy(ContactInfo)
});

const result = await agent.invoke({
    messages: [{"role": "user", "content": "Extract contact info from: John Doe, [email protected], (555) 123-4567"}]
});

result.structuredResponse;
// { name: "John Doe", email: "[email protected]", phone: "(555) 123-4567" }
提供商原生的结构化输出提供了高可靠性和严格的验证，因为模型提供商会强制执行模式。在可用时请使用它。
如果提供商对您选择的模型原生支持结构化输出，那么编写 responseFormat: contactInfoSchema 与编写 responseFormat: toolStrategy(contactInfoSchema) 在功能上是等效的。在任何一种情况下，如果不支持结构化输出，代理将回退到工具调用策略。

​
工具调用策略

对于不支持原生结构化输出的模型，LangChain 使用工具调用来实现相同的结果。这适用于所有支持工具调用的模型，也就是大多数现代模型。 要使用此策略，请配置一个 ToolStrategy： 
function toolStrategy<StructuredResponseT>(
    responseFormat:
        | JsonSchemaFormat
        | ZodSchema<StructuredResponseT>
        | (ZodSchema<StructuredResponseT> | JsonSchemaFormat)[]
    options?: ToolStrategyOptions
): ToolStrategy<StructuredResponseT>
​
schema
required
定义结构化输出格式的模式。支持：
  • Zod 模式：一个 zod 模式
  • JSON 模式：一个 JSON 模式对象
​
options.toolMessageContent
生成结构化输出时返回的工具消息的自定义内容。 如果未提供，则默认为显示结构化响应数据的消息。
​
options.handleError
包含可选 handleError 参数的选项参数，用于自定义错误处理策略。
  • true：使用默认错误模板捕获所有错误（默认）
  • False：不重试，让异常传播
  • (error: ToolStrategyError) => string | Promise<string>：使用提供的消息重试或抛出错误
import * as z from "zod";
import { createAgent, toolStrategy } from "langchain";

const ProductReview = z.object({
    rating: z.number().min(1).max(5).optional(),
    sentiment: z.enum(["positive", "negative"]),
    keyPoints: z.array(z.string()).describe("The key points of the review. Lowercase, 1-3 words each."),
});

const agent = createAgent({
    model: "openai:gpt-5",
    tools: tools,
    responseFormat: toolStrategy(ProductReview)
})

result = agent.invoke({
    "messages": [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})

console.log(result.structuredResponse);
// { "rating": 5, "sentiment": "positive", "keyPoints": ["fast shipping", "expensive"] }

​
自定义工具消息内容

toolMessageContent 参数允许您自定义生成结构化输出时出现在对话历史中的消息： 
import * as z from "zod";
import { createAgent, toolStrategy } from "langchain";

const MeetingAction = z.object({
    task: z.string().describe("The specific task to be completed"),
    assignee: z.string().describe("Person responsible for the task"),
    priority: z.enum(["low", "medium", "high"]).describe("Priority level"),
});

const agent = createAgent({
    model: "openai:gpt-5",
    tools: [],
    responseFormat: toolStrategy(MeetingAction, {
        toolMessageContent: "Action item captured and added to meeting notes!"
    })
});

const result = await agent.invoke({
    messages: [{"role": "user", "content": "From our meeting: Sarah needs to update the project timeline as soon as possible"}]
});

console.log(result);
/**
 * {
 *   messages: [
 *     { role: "user", content: "From our meeting: Sarah needs to update the project timeline as soon as possible" },
 *     { role: "assistant", content: "Action item captured and added to meeting notes!", tool_calls: [ { name: "MeetingAction", args: { task: "update the project timeline", assignee: "Sarah", priority: "high" }, id: "call_456" } ] },
 *     { role: "tool", content: "Action item captured and added to meeting notes!", tool_call_id: "call_456", name: "MeetingAction" }
 *   ],
 *   structuredResponse: { task: "update the project timeline", assignee: "Sarah", priority: "high" }
 * }
 */
如果没有 toolMessageContent，我们会看到： 
# console.log(result);
/**
 * {
 *   messages: [
 *     ...
 *     { role: "tool", content: "Returning structured response: {'task': 'update the project timeline', 'assignee': 'Sarah', 'priority': 'high'}", tool_call_id: "call_456", name: "MeetingAction" }
 *   ],
 *   structuredResponse: { task: "update the project timeline", assignee: "Sarah", priority: "high" }
 * }
 */

​
错误处理

模型在通过工具调用生成结构化输出时可能会出错。LangChain 提供了智能的重试机制来自动处理这些错误。

​
多个结构化输出错误

当模型错误地调用多个结构化输出工具时，代理会在 @[ToolMessage] 中提供错误反馈，并提示模型重试： 
import * as z from "zod";
import { createAgent, toolStrategy } from "langchain";

const ContactInfo = z.object({
    name: z.string().describe("Person's name"),
    email: z.string().describe("Email address"),
});

const EventDetails = z.object({
    event_name: z.string().describe("Name of the event"),
    date: z.string().describe("Event date"),
});

const agent = createAgent({
    model: "openai:gpt-5",
    tools: [],
    responseFormat: toolStrategy([ContactInfo, EventDetails]),
});

const result = await agent.invoke({
    messages: [
        {
        role: "user",
        content:
            "Extract info: John Doe ([email protected]) is organizing Tech Conference on March 15th",
        },
    ],
});

console.log(result);

/**
 * {
 *   messages: [
 *     { role: "user", content: "Extract info: John Doe ([email protected]) is organizing Tech Conference on March 15th" },
 *     { role: "assistant", content: "", tool_calls: [ { name: "ContactInfo", args: { name: "John Doe", email: "[email protected]" }, id: "call_1" }, { name: "EventDetails", args: { event_name: "Tech Conference", date: "March 15th" }, id: "call_2" } ] },
 *     { role: "tool", content: "Error: Model incorrectly returned multiple structured responses (ContactInfo, EventDetails) when only one is expected.\n Please fix your mistakes.", tool_call_id: "call_1", name: "ContactInfo" },
 *     { role: "tool", content: "Error: Model incorrectly returned multiple structured responses (ContactInfo, EventDetails) when only one is expected.\n Please fix your mistakes.", tool_call_id: "call_2", name: "EventDetails" },
 *     { role: "assistant", content: "", tool_calls: [ { name: "ContactInfo", args: { name: "John Doe", email: "[email protected]" }, id: "call_3" } ] },
 *     { role: "tool", content: "Returning structured response: {'name': 'John Doe', 'email': '[email protected]'}", tool_call_id: "call_3", name: "ContactInfo" }
 *   ],
 *   structuredResponse: { name: "John Doe", email: "[email protected]" }
 * }
 */

​
模式验证错误

当结构化输出与预期模式不匹配时，代理会提供具体的错误反馈： 
import * as z from "zod";
import { createAgent, toolStrategy } from "langchain";

const ProductRating = z.object({
    rating: z.number().min(1).max(5).describe("Rating from 1-5"),
    comment: z.string().describe("Review comment"),
});

const agent = createAgent({
    model: "openai:gpt-5",
    tools: [],
    responseFormat: toolStrategy(ProductRating),
});

const result = await agent.invoke({
    messages: [
        {
        role: "user",
        content: "Parse this: Amazing product, 10/10!",
        },
    ],
});

console.log(result);

/**
 * {
 *   messages: [
 *     { role: "user", content: "Parse this: Amazing product, 10/10!" },
 *     { role: "assistant", content: "", tool_calls: [ { name: "ProductRating", args: { rating: 10, comment: "Amazing product" }, id: "call_1" } ] },
 *     { role: "tool", content: "Error: Failed to parse structured output for tool 'ProductRating': 1 validation error for ProductRating\nrating\n  Input should be less than or equal to 5 [type=less_than_equal, input_value=10, input_type=int].\n Please fix your mistakes.", tool_call_id: "call_1", name: "ProductRating" },
 *     { role: "assistant", content: "", tool_calls: [ { name: "ProductRating", args: { rating: 5, comment: "Amazing product" }, id: "call_2" } ] },
 *     { role: "tool", content: "Returning structured response: {'rating': 5, 'comment': 'Amazing product'}", tool_call_id: "call_2", name: "ProductRating" }
 *   ],
 *   structuredResponse: { rating: 5, comment: "Amazing product" }
 * }
 */

​
错误处理策略

您可以使用 handleErrors 参数自定义错误处理方式： 自定义错误消息： 
const responseFormat = toolStrategy(ProductRating, {
    handleError: "Please provide a valid rating between 1-5 and include a comment."
)

// 错误消息变为：
// { role: "tool", content: "Please provide a valid rating between 1-5 and include a comment." }
仅处理特定异常： 
import { ToolInputParsingException } from "@langchain/core/tools";

const responseFormat = toolStrategy(ProductRating, {
    handleError: (error: ToolStrategyError) => {
        if (error instanceof ToolInputParsingException) {
        return "Please provide a valid rating between 1-5 and include a comment.";
        }
        return error.message;
    }
)

// 只有验证错误会使用默认消息重试：
// { role: "tool", content: "Error: Failed to parse structured output for tool 'ProductRating': ...\n Please fix your mistakes." }
处理多个异常类型： 
const responseFormat = toolStrategy(ProductRating, {
    handleError: (error: ToolStrategyError) => {
        if (error instanceof ToolInputParsingException) {
        return "Please provide a valid rating between 1-5 and include a comment.";
        }
        if (error instanceof CustomUserError) {
        return "This is a custom user error.";
        }
        return error.message;
    }
)
无错误处理： 
const responseFormat = toolStrategy(ProductRating, {
    handleError: false  // All errors raised
)
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.