并发代理#

在本节中，我们将探讨多个代理并发工作的使用。我们涵盖三个主要模式

单条消息 & 多个处理器
演示了如何让订阅同一主题的多个代理同时处理单条消息。
多条消息 & 多个处理器
说明了如何根据主题将特定消息类型路由到专用代理。
直接消息传递
侧重于在代理之间以及从运行时到代理发送消息。

import asyncio
from dataclasses import dataclass

from autogen_core import (
    AgentId,
    ClosureAgent,
    ClosureContext,
    DefaultTopicId,
    MessageContext,
    RoutedAgent,
    SingleThreadedAgentRuntime,
    TopicId,
    TypeSubscription,
    default_subscription,
    message_handler,
    type_subscription,
)

@dataclass
class Task:
    task_id: str


@dataclass
class TaskResponse:
    task_id: str
    result: str

单条消息 & 多个处理器#

第一种模式展示了如何让多个代理同时处理单条消息

每个 Processor 代理使用 default_subscription() 装饰器订阅默认主题。
当将消息发布到默认主题时，所有注册的代理将独立处理该消息。

注意

下面，我们使用 default_subscription() 装饰器订阅 Processor，还有另一种方法可以订阅代理而无需完全使用装饰器，如订阅和发布到主题中所示，这样同一个代理类可以订阅不同的主题。

@default_subscription
class Processor(RoutedAgent):
    @message_handler
    async def on_task(self, message: Task, ctx: MessageContext) -> None:
        print(f"{self._description} starting task {message.task_id}")
        await asyncio.sleep(2)  # Simulate work
        print(f"{self._description} finished task {message.task_id}")

runtime = SingleThreadedAgentRuntime()

await Processor.register(runtime, "agent_1", lambda: Processor("Agent 1"))
await Processor.register(runtime, "agent_2", lambda: Processor("Agent 2"))

runtime.start()

await runtime.publish_message(Task(task_id="task-1"), topic_id=DefaultTopicId())

await runtime.stop_when_idle()

Agent 1 starting task task-1
Agent 2 starting task task-1
Agent 1 finished task task-1
Agent 2 finished task task-1

多条消息 & 多个处理器#

其次，此模式演示了如何将不同类型的消息路由到特定处理器

UrgentProcessor 订阅“urgent”主题
NormalProcessor 订阅“normal”主题

我们使用 type_subscription() 装饰器使代理订阅特定的主题类型。

TASK_RESULTS_TOPIC_TYPE = "task-results"
task_results_topic_id = TopicId(type=TASK_RESULTS_TOPIC_TYPE, source="default")


@type_subscription(topic_type="urgent")
class UrgentProcessor(RoutedAgent):
    @message_handler
    async def on_task(self, message: Task, ctx: MessageContext) -> None:
        print(f"Urgent processor starting task {message.task_id}")
        await asyncio.sleep(1)  # Simulate work
        print(f"Urgent processor finished task {message.task_id}")

        task_response = TaskResponse(task_id=message.task_id, result="Results by Urgent Processor")
        await self.publish_message(task_response, topic_id=task_results_topic_id)


@type_subscription(topic_type="normal")
class NormalProcessor(RoutedAgent):
    @message_handler
    async def on_task(self, message: Task, ctx: MessageContext) -> None:
        print(f"Normal processor starting task {message.task_id}")
        await asyncio.sleep(3)  # Simulate work
        print(f"Normal processor finished task {message.task_id}")

        task_response = TaskResponse(task_id=message.task_id, result="Results by Normal Processor")
        await self.publish_message(task_response, topic_id=task_results_topic_id)

注册代理后，我们可以将消息发布到“urgent”和“normal”主题

runtime = SingleThreadedAgentRuntime()

await UrgentProcessor.register(runtime, "urgent_processor", lambda: UrgentProcessor("Urgent Processor"))
await NormalProcessor.register(runtime, "normal_processor", lambda: NormalProcessor("Normal Processor"))

runtime.start()

await runtime.publish_message(Task(task_id="normal-1"), topic_id=TopicId(type="normal", source="default"))
await runtime.publish_message(Task(task_id="urgent-1"), topic_id=TopicId(type="urgent", source="default"))

await runtime.stop_when_idle()

Normal processor starting task normal-1
Urgent processor starting task urgent-1
Urgent processor finished task urgent-1
Normal processor finished task normal-1

收集结果#

在前面的示例中，我们依靠控制台打印来验证任务完成情况。但是，在实际应用中，我们通常希望以编程方式收集和处理结果。

为了收集这些消息，我们将使用 ClosureAgent。我们定义了一个专用的主题 TASK_RESULTS_TOPIC_TYPE，其中 UrgentProcessor 和 NormalProcessor 都会发布其结果。然后，ClosureAgent 将处理来自该主题的消息。

queue = asyncio.Queue[TaskResponse]()


async def collect_result(_agent: ClosureContext, message: TaskResponse, ctx: MessageContext) -> None:
    await queue.put(message)


runtime.start()

CLOSURE_AGENT_TYPE = "collect_result_agent"
await ClosureAgent.register_closure(
    runtime,
    CLOSURE_AGENT_TYPE,
    collect_result,
    subscriptions=lambda: [TypeSubscription(topic_type=TASK_RESULTS_TOPIC_TYPE, agent_type=CLOSURE_AGENT_TYPE)],
)

await runtime.publish_message(Task(task_id="normal-1"), topic_id=TopicId(type="normal", source="default"))
await runtime.publish_message(Task(task_id="urgent-1"), topic_id=TopicId(type="urgent", source="default"))

await runtime.stop_when_idle()

Normal processor starting task normal-1
Urgent processor starting task urgent-1
Urgent processor finished task urgent-1
Normal processor finished task normal-1

while not queue.empty():
    print(await queue.get())

TaskResponse(task_id='urgent-1', result='Results by Urgent Processor')
TaskResponse(task_id='normal-1', result='Results by Normal Processor')

直接消息#

与之前的模式相比，此模式侧重于直接消息。在这里，我们演示了发送它们的两种方式

代理之间的直接消息传递
从运行时向特定代理发送消息

在下面的示例中需要考虑的事项

消息使用 AgentId 寻址。
发送者可以期望收到来自目标代理的响应。
我们只注册一次 WorkerAgent 类；但是，我们将任务发送给两个不同的工作人员。
- 如何做？如代理生命周期中所述，当使用 AgentId 传递消息时，运行时将提取实例或创建一个实例（如果该实例不存在）。在这种情况下，运行时在发送这两条消息时会创建两个工作人员实例。

class WorkerAgent(RoutedAgent):
    @message_handler
    async def on_task(self, message: Task, ctx: MessageContext) -> TaskResponse:
        print(f"{self.id} starting task {message.task_id}")
        await asyncio.sleep(2)  # Simulate work
        print(f"{self.id} finished task {message.task_id}")
        return TaskResponse(task_id=message.task_id, result=f"Results by {self.id}")


class DelegatorAgent(RoutedAgent):
    def __init__(self, description: str, worker_type: str):
        super().__init__(description)
        self.worker_instances = [AgentId(worker_type, f"{worker_type}-1"), AgentId(worker_type, f"{worker_type}-2")]

    @message_handler
    async def on_task(self, message: Task, ctx: MessageContext) -> TaskResponse:
        print(f"Delegator received task {message.task_id}.")

        subtask1 = Task(task_id="task-part-1")
        subtask2 = Task(task_id="task-part-2")

        worker1_result, worker2_result = await asyncio.gather(
            self.send_message(subtask1, self.worker_instances[0]), self.send_message(subtask2, self.worker_instances[1])
        )

        combined_result = f"Part 1: {worker1_result.result}, " f"Part 2: {worker2_result.result}"
        task_response = TaskResponse(task_id=message.task_id, result=combined_result)
        return task_response

runtime = SingleThreadedAgentRuntime()

await WorkerAgent.register(runtime, "worker", lambda: WorkerAgent("Worker Agent"))
await DelegatorAgent.register(runtime, "delegator", lambda: DelegatorAgent("Delegator Agent", "worker"))

runtime.start()

delegator = AgentId("delegator", "default")
response = await runtime.send_message(Task(task_id="main-task"), recipient=delegator)

print(f"Final result: {response.result}")
await runtime.stop_when_idle()

Delegator received task main-task.
worker/worker-1 starting task task-part-1
worker/worker-2 starting task task-part-2
worker/worker-1 finished task task-part-1
worker/worker-2 finished task task-part-2
Final result: Part 1: Results by worker/worker-1, Part 2: Results by worker/worker-2

其他资源#

如果您对并发处理的更多信息感兴趣，请查看代理混合模式，该模式在很大程度上依赖于并发代理。