Skip to main content
本快速入门将引导您在几分钟内从简单设置到构建功能完整的AI智能体。

构建基础智能体

首先创建一个能够回答问题并调用工具的简单智能体。该智能体将使用Claude Sonnet 4.5作为其语言模型,一个基础的天气函数作为工具,以及一个简单的提示来指导其行为。
import { createAgent, tool } from "langchain";
import * as z from "zod";

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

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-5",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in Tokyo?" }],
  })
);
对于此示例,您需要设置一个Claude (Anthropic)账户并获取API密钥。然后,在终端中设置ANTHROPIC_API_KEY环境变量。

构建真实场景智能体

接下来构建一个实用的天气预报智能体,展示关键的生产概念:
  1. 详细的系统提示以改善智能体行为
  2. 创建工具与外部数据集成
  3. 模型配置以获得一致的响应
  4. 结构化输出以获得可预测的结果
  5. 对话记忆用于类似聊天的交互
  6. 创建并运行智能体创建一个功能完整的智能体
让我们逐步进行:
1

定义系统提示

系统提示定义了智能体的角色和行为。保持其具体且可操作:
const systemPrompt = `You are an expert weather forecaster, who speaks in puns.

You have access to two tools:

- get_weather_for_location: use this to get the weather for a specific location
- get_user_location: use this to get the user's location

If a user asks you for the weather, make sure you know the location. If you can tell from the question that they mean wherever they are, use the get_user_location tool to find their location.`;
2

创建工具

工具是您的智能体可以调用的函数。通常,工具会希望连接到外部系统,并将依赖运行时配置来实现这一点。请注意这里的getUserLocation工具正是这样做的:
import { type Runtime } from "@langchain/langgraph";
import { tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather_for_location",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

type AgentRuntime = Runtime<{ user_id: string }>;

const getUserLocation = tool(
  (_, config: AgentRuntime) => {
    const { user_id } = config.context;
    return user_id === "1" ? "Florida" : "SF";
  },
  {
    name: "get_user_location",
    description: "Retrieve user information based on user ID",
  }
);
Zod是一个用于验证和解析预定义模式的库。您可以使用它来定义工具的输入模式,以确保智能体仅使用正确的参数调用工具。或者,您可以将schema属性定义为JSON schema对象。请注意,JSON模式不会在运行时被验证。
const getWeather = tool(
  ({ city }) => `It's always sunny in ${city}!`,
  {
    name: "get_weather_for_location",
    description: "Get the weather for a given city",
    schema: {
      type: "object",
      properties: {
        city: {
          type: "string",
          description: "The city to get the weather for"
        }
      },
      required: ["city"]
    },
  }
);
3

配置模型

为您的用例设置具有正确参数语言模型
import { initChatModel } from "langchain";

const model = await initChatModel(
  "anthropic:claude-sonnet-4-5",
  { temperature: 0.5, timeout: 10, maxTokens: 1000 }
);
4

定义响应格式

如果需要智能体响应匹配特定模式,可以选择定义结构化响应格式。
const responseFormat = z.object({
  punny_response: z.string(),
  weather_conditions: z.string().optional(),
});
5

添加记忆

为您的智能体添加记忆,以在交互之间保持状态。这允许 智能体记住之前的对话和上下文。
import { MemorySaver } from "@langchain/langgraph";

const checkpointer = new MemorySaver();
在生产环境中,请使用持久化检查点保存到数据库。 有关更多详细信息,请参阅添加和管理记忆
6

创建并运行智能体

现在使用所有组件组装您的智能体并运行它!
import { createAgent } from "langchain";

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-5",
  prompt: systemPrompt,
  tools: [getUserLocation, getWeather],
  responseFormat,
  checkpointer,
});

// `thread_id`是给定对话的唯一标识符。
const config = {
  configurable: { thread_id: "1" },
  context: { user_id: "1" },
};

const response = await agent.invoke(
  { messages: [{ role: "user", content: "what is the weather outside?" }] },
  config
);
console.log(response.structuredResponse);
// {
//   punny_response: "Florida is still having a 'sun-derful' day ...",
//   weather_conditions: "It's always sunny in Florida!"
// }

// 注意,我们可以使用相同的`thread_id`继续对话。
const thankYouResponse = await agent.invoke(
  { messages: [{ role: "user", content: "thank you!" }] },
  config
);
console.log(thankYouResponse.structuredResponse);
// {
//   punny_response: "You're 'thund-erfully' welcome! ...",
//   weather_conditions: undefined
// }
恭喜!您现在拥有了一个能够:
  • 理解上下文并记住对话
  • 智能使用多个工具
  • 以一致格式提供结构化响应
  • 通过上下文处理用户特定信息
  • 在交互间维护对话状态的AI智能体

Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.