快速入门

项目与虚拟环境创建

你只需执行一次。

mkdir my_project
cd my_project
python -m venv .venv

虚拟环境激活

每次启动新的终端会话都需执行。

source .venv/bin/activate

Agents SDK 安装

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

OpenAI API 密钥设置

如果还没有，请按照这些说明创建一个 OpenAI API 密钥。

export OPENAI_API_KEY=sk-...

第一个智能体创建

智能体由 instructions、名称以及可选配置（例如 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",
)

任务转移定义

在每个智能体上，你可以定义一组可用的外发任务转移选项，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]
)

智能体编排运行

我们来检查工作流是否运行，以及分诊智能体是否能在两个专家型智能体之间正确路由。

from agents import Runner

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

安全防护措施添加

你可以定义自定义安全防护措施，在输入或输出阶段运行。

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,
    )

综合运行

让我们将其整合起来，使用任务转移和输入安全防护措施运行整个工作流。

from agents import Agent, InputGuardrail, GuardrailFunctionOutput, Runner
from agents.exceptions import InputGuardrailTripwireTriggered
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():
    # Example 1: History question
    try:
        result = await Runner.run(triage_agent, "who was the first president of the united states?")
        print(result.final_output)
    except InputGuardrailTripwireTriggered as e:
        print("Guardrail blocked this input:", e)

    # Example 2: General/philosophical question
    try:
        result = await Runner.run(triage_agent, "What is the meaning of life?")
        print(result.final_output)
    except InputGuardrailTripwireTriggered as e:
        print("Guardrail blocked this input:", e)

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

追踪查看

若要查看智能体运行期间发生的情况，请前往 OpenAI 控制台中的追踪查看器查看运行追踪。

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Agents。
了解运行智能体。
了解tools、安全防护措施和模型。