快速开始

项目设置

创建项目并初始化 npm。此步骤只需执行一次。
Terminal window
```
mkdir my_project
cd my_project
npm init -y
```
安装 Agents SDK。
Terminal window
```
npm install @openai/agents zod@3
```
设置 OpenAI API key。如果还没有，请按照这些说明创建一个 OpenAI API key。
Terminal window
```
export OPENAI_API_KEY=sk-...
```
或者，您也可以调用 setDefaultOpenAIKey('<api key>') 以编程方式设置密钥，并使用 setTracingExportApiKey('<api key>') 进行追踪。详细信息参见SDK 配置。

第一个智能体

智能体由 instructions 和名称定义。

import { Agent } from '@openai/agents';

const agent = new Agent({
  name: 'History Tutor',
  instructions:
    'You provide assistance with historical queries. Explain important events and context clearly.',
});

运行第一个智能体

您可以使用 run 方法来运行智能体。通过传入要启动的智能体和要传递的输入来触发一次运行。

这将返回一个执行结果，其中包含最终输出以及该次运行期间执行的任何操作。

import { Agent, run } from '@openai/agents';

const agent = new Agent({
  name: 'History Tutor',
  instructions:
    'You provide assistance with historical queries. Explain important events and context clearly.',
});

const result = await run(agent, 'When did sharks first appear?');

console.log(result.finalOutput);

为智能体提供工具

您可以为智能体提供工具以查询信息或执行操作。

import { Agent, tool } from '@openai/agents';

const historyFunFact = tool({
  // The name of the tool will be used by the agent to tell what tool to use.
  name: 'history_fun_fact',
  // The description is used to describe **when** to use the tool by telling it **what** it does.
  description: 'Give a fun fact about a historical event',
  // This tool takes no parameters, so we provide an empty Zod Object.
  parameters: z.object({}),
  execute: async () => {
    // The output will be returned back to the Agent to use
    return 'Sharks are older than trees.';
  },
});

const agent = new Agent({
  name: 'History Tutor',
  instructions:
    'You provide assistance with historical queries. Explain important events and context clearly.',
  // Adding the tool to the agent
  tools: [historyFunFact],
});

添加更多智能体

可以用类似方式定义更多智能体，将问题拆解为更小的部分，让智能体更专注于当前任务。还可以在智能体上定义所用模型，从而针对不同问题使用不同模型。

const historyTutorAgent = new Agent({
  name: 'History Tutor',
  instructions:
    'You provide assistance with historical queries. Explain important events and context clearly.',
});

const mathTutorAgent = new Agent({
  name: 'Math Tutor',
  instructions:
    'You provide help with math problems. Explain your reasoning at each step and include examples',
});

交接定义

为在多个智能体之间进行编排，您可以为智能体定义 handoffs。这将使智能体能够将对话传递给下一个智能体。这会在运行过程中自动发生。

// Using the Agent.create method to ensures type safety for the final output
const triageAgent = Agent.create({
  name: 'Triage Agent',
  instructions:
    "You determine which agent to use based on the user's homework question",
  handoffs: [historyTutorAgent, mathTutorAgent],
});

运行结束后，您可以通过查看结果中的 finalAgent 属性来了解哪个智能体生成了最终响应。

智能体编排运行

Runner 负责处理各个智能体的执行、可能的交接以及工具执行。

import { run } from '@openai/agents';

async function main() {
  const result = await run(triageAgent, 'What is the capital of France?');
  console.log(result.finalOutput);
}

main().catch((err) => console.error(err));

整合

让我们把以上内容整合成一个完整示例。将其放入 index.js 文件并运行。

import { Agent, run } from '@openai/agents';

const historyTutorAgent = new Agent({
  name: 'History Tutor',
  instructions:
    'You provide assistance with historical queries. Explain important events and context clearly.',
});

const mathTutorAgent = new Agent({
  name: 'Math Tutor',
  instructions:
    'You provide help with math problems. Explain your reasoning at each step and include examples',
});

const triageAgent = new Agent({
  name: 'Triage Agent',
  instructions:
    "You determine which agent to use based on the user's homework question",
  handoffs: [historyTutorAgent, mathTutorAgent],
});

async function main() {
  const result = await run(triageAgent, 'What is the capital of France?');
  console.log(result.finalOutput);
}

main().catch((err) => console.error(err));

查看追踪

Agents SDK 会自动为您生成追踪。您可以据此审查智能体的运行情况、调用了哪些工具或将会话交接给了哪个智能体。

要查看智能体运行期间发生的情况，请前往 OpenAI Dashboard 中的 Trace viewer。

后续步骤

了解如何构建更复杂的智能体流程：

了解如何配置智能体。
了解运行智能体。
了解工具、护栏和模型。