Skip to main content

Documentation Index

Fetch the complete documentation index at: https://nvd-54.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

当你使用 LangChain 构建和运行智能体时,你需要了解它们的行为:它们调用了哪些工具、生成了什么提示词以及它们如何做出决策。使用 createAgent 构建的 LangChain 智能体通过 LangSmith 自动支持追踪,LangSmith 是一个用于捕获、调试、评估和监控 LLM 应用行为的平台。 追踪记录智能体执行的每一步,从初始用户输入到最终响应,包括所有工具调用、模型交互和决策点。这些执行数据帮助你调试问题、评估不同输入的性能,并监控生产中的使用模式。 本指南向你展示如何为 LangChain 智能体启用追踪并使用 LangSmith 分析其执行。

前提条件

开始之前,请确保你具备以下条件:

启用追踪

所有 LangChain 智能体自动支持 LangSmith 追踪。要启用它,设置以下环境变量:
export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY=<your-api-key>

快速入门

无需额外代码即可将追踪记录到 LangSmith。只需像平常一样运行你的智能体代码:
import { createAgent } from "@langchain/agents";

function sendEmail(to: string, subject: string, body: string): string {
    // ... 邮件发送逻辑
    return `Email sent to ${to}`;
}

function searchWeb(query: string): string {
    // ... 网络搜索逻辑
    return `Search results for: ${query}`;
}

const agent = createAgent({
    model: "gpt-5.4",
    tools: [sendEmail, searchWeb],
    systemPrompt: "You are a helpful assistant that can send emails and search the web."
});

// 运行智能体 - 所有步骤将自动追踪
const response = await agent.invoke({
    messages: [{ role: "user", content: "搜索最新的 AI 新闻并将摘要发送到 john@example.com" }]
});
默认情况下,追踪将记录到名为 default 的项目中。要配置自定义项目名称,请参阅记录到项目

Trace selectively

You may opt to trace specific invocations or parts of your application using LangSmith’s tracing_context context manager:
import { LangChainTracer } from "@langchain/core/tracers/tracer_langchain";

// This WILL be traced
const tracer = new LangChainTracer();
await agent.invoke(
  {
    messages: [{role: "user", content: "Send a test email to alice@example.com"}]
  },
  { callbacks: [tracer] }
);

// This will NOT be traced (if LANGSMITH_TRACING is not set)
await agent.invoke(
  {
    messages: [{role: "user", content: "Send another email"}]
  }
);

Log to a project

You can set a custom project name for your entire application by setting the LANGSMITH_PROJECT environment variable:
export LANGSMITH_PROJECT=my-agent-project
You can set the project name programmatically for specific operations:
import { LangChainTracer } from "@langchain/core/tracers/tracer_langchain";

const tracer = new LangChainTracer({ projectName: "email-agent-test" });
await agent.invoke(
  {
    messages: [{role: "user", content: "Send a test email to alice@example.com"}]
  },
  { callbacks: [tracer] }
);

Add metadata to traces

You can annotate your traces with custom metadata and tags:
import { LangChainTracer } from "@langchain/core/tracers/tracer_langchain";

const tracer = new LangChainTracer({ projectName: "email-agent-test" });
await agent.invoke(
  {
    messages: [{role: "user", content: "Send a test email to alice@example.com"}]
  },
  {
    tags: ["production", "email-assistant", "v1.0"],
    metadata: {
      userId: "user123",
      sessionId: "session456",
      environment: "production"
    }
  },
);

This custom metadata and tags will be attached to the trace in LangSmith.
要了解更多关于 how to use traces to debug, evaluate, and monitor your agents, see the LangSmith documentation.