跳转到内容

快速开始

  1. 创建一个项目并初始化 npm。此操作只需进行一次。

    Terminal window
    mkdir my_project
    cd my_project
    npm init -y
  2. 安装 Agents SDK。

    Terminal window
    npm install @openai/agents zod@3
  3. 设置 OpenAI API key。如果你还没有,请按照这些说明创建一个 OpenAI API key。

    Terminal window
    export OPENAI_API_KEY=sk-...

    或者,你可以调用 setDefaultOpenAIKey('<api key>') 以编程方式设置密钥,并使用 setTracingExportApiKey('<api key>') 用于追踪。 更多详情参见SDK 配置

智能体通过 instructions 和名称来定义。

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.',
});

你可以使用 run 方法来运行智能体。通过传入要启动的智能体和要传入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在该次运行过程中执行的所有动作。

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);

你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],
});

可以以类似方式定义更多智能体,将问题拆解为更小的部分,让你的智能体更加专注于当前任务。还可以通过在智能体上定义模型来针对不同问题使用不同的模型。

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',
});

为了在多个智能体之间进行编排,你可以为智能体定义 handoffs。这将使智能体能够将对话交接给下一个智能体。这将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],
});

运行完成后,你可以查看执行结果上的 finalAgent 属性来确定哪个智能体生成了最终响应。

Runner 负责处理各个智能体的执行、任何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));

让我们把所有内容整合为一个完整示例。将其放入你的 index.js 文件并运行。

快速上手
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));

Agents SDK 会自动为你生成追踪。这使你能够审查智能体的运行情况、调用了哪些工具或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 的 Trace viewer

了解如何构建更复杂的智能体流程: