跳转至

快速入门

创建项目和虚拟环境

只需执行一次

mkdir my_project
cd my_project
python -m venv .venv

激活虚拟环境

每次开启新的终端会话时都需要执行

source .venv/bin/activate

安装Agents SDK

pip install openai-agents # or `uv add openai-agents`, etc

设置OpenAI API密钥

如果没有API密钥，请按照这些说明创建

export OPENAI_API_KEY=sk-...

创建第一个智能体

智能体通过指令、名称和可选配置（如model_config）定义

from agents import Agent

agent = Agent(
    name="Math Tutor",
    instructions="You provide help with math problems. Explain your reasoning at each step and include examples",
)

添加更多智能体

可以同样方式定义更多智能体。handoff_descriptions为交接路由提供额外上下文

from agents import Agent

history_tutor_agent = Agent(
    name="History Tutor",
    handoff_description="Specialist agent for historical questions",
    instructions="You provide assistance with historical queries. Explain important events and context clearly.",
)

math_tutor_agent = Agent(
    name="Math Tutor",
    handoff_description="Specialist agent for math questions",
    instructions="You provide help with math problems. Explain your reasoning at each step and include examples",
)

定义交接

在每个智能体上，可以定义一组交接选项供其选择以决定如何推进任务

triage_agent = Agent(
    name="Triage Agent",
    instructions="You determine which agent to use based on the user's homework question",
    handoffs=[history_tutor_agent, math_tutor_agent]
)

运行智能体编排

让我们检查工作流是否正常运行，以及分诊智能体能否正确在两个专业智能体间路由

from agents import Runner

async def main():
    result = await Runner.run(triage_agent, "What is the capital of France?")
    print(result.final_output)

添加防护栏

可以定义在输入或输出上运行的自定义防护栏

from agents import GuardrailFunctionOutput, Agent, Runner
from pydantic import BaseModel

class HomeworkOutput(BaseModel):
    is_homework: bool
    reasoning: str

guardrail_agent = Agent(
    name="Guardrail check",
    instructions="Check if the user is asking about homework.",
    output_type=HomeworkOutput,
)

async def homework_guardrail(ctx, agent, input_data):
    result = await Runner.run(guardrail_agent, input_data, context=ctx.context)
    final_output = result.final_output_as(HomeworkOutput)
    return GuardrailFunctionOutput(
        output_info=final_output,
        tripwire_triggered=not final_output.is_homework,
    )

整合所有内容

让我们整合所有内容并运行完整工作流，使用交接和输入防护栏

from agents import Agent, InputGuardrail, GuardrailFunctionOutput, Runner
from pydantic import BaseModel
import asyncio

class HomeworkOutput(BaseModel):
    is_homework: bool
    reasoning: str

guardrail_agent = Agent(
    name="Guardrail check",
    instructions="Check if the user is asking about homework.",
    output_type=HomeworkOutput,
)

math_tutor_agent = Agent(
    name="Math Tutor",
    handoff_description="Specialist agent for math questions",
    instructions="You provide help with math problems. Explain your reasoning at each step and include examples",
)

history_tutor_agent = Agent(
    name="History Tutor",
    handoff_description="Specialist agent for historical questions",
    instructions="You provide assistance with historical queries. Explain important events and context clearly.",
)


async def homework_guardrail(ctx, agent, input_data):
    result = await Runner.run(guardrail_agent, input_data, context=ctx.context)
    final_output = result.final_output_as(HomeworkOutput)
    return GuardrailFunctionOutput(
        output_info=final_output,
        tripwire_triggered=not final_output.is_homework,
    )

triage_agent = Agent(
    name="Triage Agent",
    instructions="You determine which agent to use based on the user's homework question",
    handoffs=[history_tutor_agent, math_tutor_agent],
    input_guardrails=[
        InputGuardrail(guardrail_function=homework_guardrail),
    ],
)

async def main():
    result = await Runner.run(triage_agent, "who was the first president of the united states?")
    print(result.final_output)

    result = await Runner.run(triage_agent, "what is life")
    print(result.final_output)

if __name__ == "__main__":
    asyncio.run(main())

查看追踪记录

要查看智能体运行期间发生的情况，请导航至OpenAI仪表板中的追踪查看器查看智能体运行的追踪记录

后续步骤

学习如何构建更复杂的智能体流程：