Mixture of Agents# 混合代理
Mixture of Agents is a multi-agent design pattern
that models after the feed-forward neural network architecture.
混合代理是一种多代理设计模式，其结构模仿了前馈神经网络架构。
The pattern consists of two types of agents: worker agents and a single orchestrator agent.
Worker agents are organized into multiple layers, with each layer consisting of a fixed number of worker agents.
Messages from the worker agents in a previous layer are concatenated and sent to
all the worker agents in the next layer.
模式由两种类型的代理组成：工作代理和一个单独的协调代理。工作代理被组织成多个层级，每个层级包含固定数量的工作代理。来自前一层级的工作代理的消息被连接起来，并发送给下一层级中的所有工作代理。
This example implements the Mixture of Agents pattern using the core library
following the original implementation of multi-layer mixture of agents.
本示例使用核心库实现了混合代理模式，遵循多层混合代理的原版实现。
Here is a high-level procedure overview of the pattern:
这里是对该模式的高级流程概述：
The orchestrator agent takes input a user task and first dispatches it to the worker agents in the first layer.
调度代理接收用户任务，首先将其派发到第一层的工人代理。The worker agents in the first layer process the task and return the results to the orchestrator agent.
第一层的工人代理处理任务并将结果返回给编排代理。The orchestrator agent then synthesizes the results from the first layer and dispatches an updated task with the previous results to the worker agents in the second layer.
调度代理随后综合第一层的结果，并将带有先前结果的更新任务派发到第二层的工人代理。The process continues until the final layer is reached.
过程持续进行，直到达到最外层。In the final layer, the orchestrator agent aggregates the results from previous layer and returns a single final result to the user.
在最后一层，协调器代理汇总之前层的输出，并向用户返回一个单一最终结果。
We use the direct messaging API send_message() to implement this pattern.
This makes it easier to add more features like worker task cancellation and error handling in the future.
我们使用直接消息 API send_message() 来实现此模式。这使得未来添加更多功能，如工作任务取消和错误处理，变得更加容易。
import asyncio
from dataclasses import dataclass
from typing import List
from autogen_core import AgentId, MessageContext, RoutedAgent, SingleThreadedAgentRuntime, message_handler
from autogen_core.models import ChatCompletionClient, SystemMessage, UserMessage
from autogen_ext.models.openai import OpenAIChatCompletionClient
Message Protocol# 消息协议 #
The agents communicate using the following messages:
代理使用以下消息进行通信：
@dataclass
class WorkerTask:
task: str
previous_results: List[str]
@dataclass
class WorkerTaskResult:
result: str
@dataclass
class UserTask:
task: str
@dataclass
class FinalResult:
result: str
Worker Agent# 工人代理编号
Each worker agent receives a task from the orchestrator agent and processes them
indepedently.
Once the task is completed, the worker agent returns the result.
每个工作代理从编排代理那里接收任务并独立处理。一旦任务完成，工作代理返回结果。
class WorkerAgent(RoutedAgent):
def __init__(
self,
model_client: ChatCompletionClient,
) -> None:
super().__init__(description="Worker Agent")
self._model_client = model_client
@message_handler
async def handle_task(self, message: WorkerTask, ctx: MessageContext) -> WorkerTaskResult:
if message.previous_results:
# If previous results are provided, we need to synthesize them to create a single prompt.
system_prompt = "You have been provided with a set of responses from various open-source models to the latest user query. Your task is to synthesize these responses into a single, high-quality response. It is crucial to critically evaluate the information provided in these responses, recognizing that some of it may be biased or incorrect. Your response should not simply replicate the given answers but should offer a refined, accurate, and comprehensive reply to the instruction. Ensure your response is well-structured, coherent, and adheres to the highest standards of accuracy and reliability.\n\nResponses from models:"
system_prompt += "\n" + "\n\n".join([f"{i+1}. {r}" for i, r in enumerate(message.previous_results)])
model_result = await self._model_client.create(
[SystemMessage(content=system_prompt), UserMessage(content=message.task, source="user")]
)
else:
# If no previous results are provided, we can simply pass the user query to the model.
model_result = await self._model_client.create([UserMessage(content=message.task, source="user")])
assert isinstance(model_result.content, str)
print(f"{'-'*80}\nWorker-{self.id}:\n{model_result.content}")
return WorkerTaskResult(result=model_result.content)
Orchestrator Agent# 编排代理 #
The orchestrator agent receives tasks from the user and distributes them to the worker agents,
iterating over multiple layers of worker agents. Once all worker agents have processed the task,
the orchestrator agent aggregates the results and publishes the final result.
调度代理从用户接收任务并将它们分配给工作代理，遍历多个工作代理层。一旦所有工作代理都处理完任务，调度代理汇总结果并发布最终结果。
class OrchestratorAgent(RoutedAgent):
def __init__(
self,
model_client: ChatCompletionClient,
worker_agent_types: List[str],
num_layers: int,
) -> None:
super().__init__(description="Aggregator Agent")
self._model_client = model_client
self._worker_agent_types = worker_agent_types
self._num_layers = num_layers
@message_handler
async def handle_task(self, message: UserTask, ctx: MessageContext) -> FinalResult:
print(f"{'-'*80}\nOrchestrator-{self.id}:\nReceived task: {message.task}")
# Create task for the first layer.
worker_task = WorkerTask(task=message.task, previous_results=[])
# Iterate over layers.
for i in range(self._num_layers - 1):
# Assign workers for this layer.
worker_ids = [
AgentId(worker_type, f"{self.id.key}/layer_{i}/worker_{j}")
for j, worker_type in enumerate(self._worker_agent_types)
]
# Dispatch tasks to workers.
print(f"{'-'*80}\nOrchestrator-{self.id}:\nDispatch to workers at layer {i}")
results = await asyncio.gather(*[self.send_message(worker_task, worker_id) for worker_id in worker_ids])
print(f"{'-'*80}\nOrchestrator-{self.id}:\nReceived results from workers at layer {i}")
# Prepare task for the next layer.
worker_task = WorkerTask(task=message.task, previous_results=[r.result for r in results])
# Perform final aggregation.
print(f"{'-'*80}\nOrchestrator-{self.id}:\nPerforming final aggregation")
system_prompt = "You have been provided with a set of responses from various open-source models to the latest user query. Your task is to synthesize these responses into a single, high-quality response. It is crucial to critically evaluate the information provided in these responses, recognizing that some of it may be biased or incorrect. Your response should not simply replicate the given answers but should offer a refined, accurate, and comprehensive reply to the instruction. Ensure your response is well-structured, coherent, and adheres to the highest standards of accuracy and reliability.\n\nResponses from models:"
system_prompt += "\n" + "\n\n".join([f"{i+1}. {r}" for i, r in enumerate(worker_task.previous_results)])
model_result = await self._model_client.create(
[SystemMessage(content=system_prompt), UserMessage(content=message.task, source="user")]
)
assert isinstance(model_result.content, str)
return FinalResult(result=model_result.content)
Running Mixture of Agents#
运行混合智能体
Let’s run the mixture of agents on a math task. You can change the task to make it more challenging, for example, by trying tasks from the International Mathematical Olympiad.
让我们在一个数学任务上运行代理混合。你可以更改任务以使其更具挑战性，例如，尝试国际数学奥林匹克竞赛的任务。
task = (
"I have 432 cookies, and divide them 3:4:2 between Alice, Bob, and Charlie. How many cookies does each person get?"
)
Let’s set up the runtime with 3 layers of worker agents, each layer consisting of 3 worker agents.
We only need to register a single worker agent types, “worker”, because we are using
the same model client configuration (i.e., gpt-4o-mini) for all worker agents.
If you want to use different models, you will need to register multiple worker agent types,
one for each model, and update the worker_agent_types list in the orchestrator agent’s
factory function.
让我们设置运行时，使用 3 层工作代理，每层包含 3 个工作代理。我们只需要注册一个工作代理类型，“worker”，因为我们为所有工作代理使用相同的模型客户端配置（即，gpt-4o-mini）。如果您想使用不同的模型，您需要注册多个工作代理类型，每个模型一个，并更新编排代理工厂函数中的 worker_agent_types 列表。
The instances of worker agents are automatically created when the orchestrator agent
dispatches tasks to them.
See Agent Identity and Lifecycle
for more information on agent lifecycle.
工作代理实例在编排代理将任务分配给它们时自动创建。有关代理生命周期的更多信息，请参阅代理身份和生命周期。
runtime = SingleThreadedAgentRuntime()
await WorkerAgent.register(
runtime, "worker", lambda: WorkerAgent(model_client=OpenAIChatCompletionClient(model="gpt-4o-mini"))
)
await OrchestratorAgent.register(
runtime,
"orchestrator",
lambda: OrchestratorAgent(
model_client=OpenAIChatCompletionClient(model="gpt-4o"), worker_agent_types=["worker"] * 3, num_layers=3
),
)
runtime.start()
result = await runtime.send_message(UserTask(task=task), AgentId("orchestrator", "default"))
await runtime.stop_when_idle()
print(f"{'-'*80}\nFinal result:\n{result.result}")
--------------------------------------------------------------------------------
Orchestrator-orchestrator:default:
Received task: I have 432 cookies, and divide them 3:4:2 between Alice, Bob, and Charlie. How many cookies does each person get?
--------------------------------------------------------------------------------
Orchestrator-orchestrator:default:
Dispatch to workers at layer 0
--------------------------------------------------------------------------------
Worker-worker:default/layer_0/worker_1:
To divide 432 cookies in the ratio of 3:4:2 between Alice, Bob, and Charlie, you first need to determine the total number of parts in the ratio.
Add the parts together:
\[ 3 + 4 + 2 = 9 \]
Now, you can find the value of one part by dividing the total number of cookies by the total number of parts:
\[ \text{Value of one part} = \frac{432}{9} = 48 \]
Now, multiply the value of one part by the number of parts for each person:
- For Alice (3 parts):
\[ 3 \times 48 = 144 \]
- For Bob (4 parts):
\[ 4 \times 48 = 192 \]
- For Charlie (2 parts):
\[ 2 \times 48 = 96 \]
Thus, the number of cookies each person gets is:
- Alice: 144 cookies
- Bob: 192 cookies
- Charlie: 96 cookies
--------------------------------------------------------------------------------
Worker-worker:default/layer_0/worker_0:
To divide 432 cookies in the ratio of 3:4:2 between Alice, Bob, and Charlie, we will first determine the total number of parts in the ratio:
\[
3 + 4 + 2 = 9 \text{ parts}
\]
Next, we calculate the value of one part by dividing the total number of cookies by the total number of parts:
\[
\text{Value of one part} = \frac{432}{9} = 48
\]
Now, we can find out how many cookies each person receives by multiplying the value of one part by the number of parts each person receives:
- For Alice (3 parts):
\[
3 \times 48 = 144 \text{ cookies}
\]
- For Bob (4 parts):
\[
4 \times 48 = 192 \text{ cookies}
\]
- For Charlie (2 parts):
\[
2 \times 48 = 96 \text{ cookies}
\]
Thus, the number of cookies each person gets is:
- **Alice**: 144 cookies
- **Bob**: 192 cookies
- **Charlie**: 96 cookies
--------------------------------------------------------------------------------
Worker-worker:default/layer_0/worker_2:
To divide the cookies in the ratio of 3:4:2, we first need to find the total parts in the ratio.
The total parts are:
- Alice: 3 parts
- Bob: 4 parts
- Charlie: 2 parts
Adding these parts together gives:
\[ 3 + 4 + 2 = 9 \text{ parts} \]
Next, we can determine how many cookies each part represents by dividing the total number of cookies by the total parts:
\[ \text{Cookies per part} = \frac{432 \text{ cookies}}{9 \text{ parts}} = 48 \text{ cookies/part} \]
Now we can calculate the number of cookies for each person:
- Alice's share:
\[ 3 \text{ parts} \times 48 \text{ cookies/part} = 144 \text{ cookies} \]
- Bob's share:
\[ 4 \text{ parts} \times 48 \text{ cookies/part} = 192 \text{ cookies} \]
- Charlie's share:
\[ 2 \text{ parts} \times 48 \text{ cookies/part} = 96 \text{ cookies} \]
So, the final distribution of cookies is:
- Alice: 144 cookies
- Bob: 192 cookies
- Charlie: 96 cookies
--------------------------------------------------------------------------------
Orchestrator-orchestrator:default:
Received results from workers at layer 0
--------------------------------------------------------------------------------
Orchestrator-orchestrator:default:
Dispatch to workers at layer 1
--------------------------------------------------------------------------------
Worker-worker:default/layer_1/worker_2:
To divide 432 cookies in the ratio of 3:4:2 among Alice, Bob, and Charlie, follow these steps:
1. **Determine the total number of parts in the ratio**:
\[
3 + 4 + 2 = 9 \text{ parts}
\]
2. **Calculate the value of one part** by dividing the total number of cookies by the total number of parts:
\[
\text{Value of one part} = \frac{432}{9} = 48
\]
3. **Calculate the number of cookies each person receives** by multiplying the value of one part by the number of parts each individual gets:
- **For Alice (3 parts)**:
\[
3 \times 48 = 144 \text{ cookies}
\]
- **For Bob (4 parts)**:
\[
4 \times 48 = 192 \text{ cookies}
\]
- **For Charlie (2 parts)**:
\[
2 \times 48 = 96 \text{ cookies}
\]
Thus, the final distribution of cookies is:
- **Alice**: 144 cookies
- **Bob**: 192 cookies
- **Charlie**: 96 cookies
--------------------------------------------------------------------------------
Worker-worker:default/layer_1/worker_0:
To divide 432 cookies among Alice, Bob, and Charlie in the ratio of 3:4:2, we can follow these steps:
1. **Calculate the Total Parts**:
Add the parts of the ratio together:
\[
3 + 4 + 2 = 9 \text{ parts}
\]
2. **Determine the Value of One Part**:
Divide the total number of cookies by the total number of parts:
\[
\text{Value of one part} = \frac{432 \text{ cookies}}{9 \text{ parts}} = 48 \text{ cookies/part}
\]
3. **Calculate Each Person's Share**:
- **Alice's Share** (3 parts):
\[
3 \times 48 = 144 \text{ cookies}
\]
- **Bob's Share** (4 parts):
\[
4 \times 48 = 192 \text{ cookies}
\]
- **Charlie's Share** (2 parts):
\[
2 \times 48 = 96 \text{ cookies}
\]
4. **Final Distribution**:
- Alice: 144 cookies
- Bob: 192 cookies
- Charlie: 96 cookies
Thus, the distribution of cookies is:
- **Alice**: 144 cookies
- **Bob**: 192 cookies
- **Charlie**: 96 cookies
--------------------------------------------------------------------------------
Worker-worker:default/layer_1/worker_1:
To divide 432 cookies among Alice, Bob, and Charlie in the ratio of 3:4:2, we first need to determine the total number of parts in this ratio.
1. **Calculate Total Parts:**
\[
3 \text{ (Alice)} + 4 \text{ (Bob)} + 2 \text{ (Charlie)} = 9 \text{ parts}
\]
2. **Determine the Value of One Part:**
Next, we'll find out how many cookies correspond to one part by dividing the total number of cookies by the total number of parts:
\[
\text{Value of one part} = \frac{432 \text{ cookies}}{9 \text{ parts}} = 48 \text{ cookies/part}
\]
3. **Calculate the Share for Each Person:**
- **Alice's Share (3 parts):**
\[
3 \times 48 = 144 \text{ cookies}
\]
- **Bob's Share (4 parts):**
\[
4 \times 48 = 192 \text{ cookies}
\]
- **Charlie’s Share (2 parts):**
\[
2 \times 48 = 96 \text{ cookies}
\]
4. **Summary of the Distribution:**
- **Alice:** 144 cookies
- **Bob:** 192 cookies
- **Charlie:** 96 cookies
In conclusion, Alice receives 144 cookies, Bob receives 192 cookies, and Charlie receives 96 cookies.
--------------------------------------------------------------------------------
Orchestrator-orchestrator:default:
Received results from workers at layer 1
--------------------------------------------------------------------------------
Orchestrator-orchestrator:default:
Performing final aggregation
--------------------------------------------------------------------------------
Final result:
To divide 432 cookies among Alice, Bob, and Charlie in the ratio of 3:4:2, follow these steps:
1. **Calculate the Total Parts in the Ratio:**
Add the parts of the ratio together:
\[
3 + 4 + 2 = 9
\]
2. **Determine the Value of One Part:**
Divide the total number of cookies by the total number of parts:
\[
\text{Value of one part} = \frac{432}{9} = 48 \text{ cookies/part}
\]
3. **Calculate Each Person's Share:**
- **Alice's Share (3 parts):**
\[
3 \times 48 = 144 \text{ cookies}
\]
- **Bob's Share (4 parts):**
\[
4 \times 48 = 192 \text{ cookies}
\]
- **Charlie's Share (2 parts):**
\[
2 \times 48 = 96 \text{ cookies}
\]
Therefore, the distribution of cookies is as follows:
- **Alice:** 144 cookies
- **Bob:** 192 cookies
- **Charlie:** 96 cookies
In summary, Alice gets 144 cookies, Bob gets 192 cookies, and Charlie gets 96 cookies.