快速开始
创建项目和虚拟环境
你只需执行一次。
激活虚拟环境
每次开启新的终端会话都要执行。
安装 Agents SDK
设置 OpenAI API 密钥
如果你还没有,按照这些说明创建一个 OpenAI API key。
创建你的第一个智能体
智能体由 instructions、名称和可选配置(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",
)
再添加几个智能体
其他智能体可以用相同方式定义。handoff_descriptions 为确定任务转移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",
)
定义你的任务转移
在每个智能体上,你可以定义一个外发任务转移选项清单,供智能体选择以决定如何推进其任务。
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运行,以及分诊智能体是否在两个专家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)
添加安全防护措施
你可以在输入或输出上定义自定义安全防护措施。
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,
)
整合运行
让我们把这些组合起来,运行整个工作流,使用任务转移和输入安全防护措施。
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())
查看追踪
要回顾智能体运行期间发生的事情,请前往 OpenAI 控制台中的追踪查看器查看你的运行追踪。
后续步骤
了解如何构建更复杂的智能体流程: