Orquestación concurrente

La orquestación simultánea permite que varios agentes funcionen en la misma tarea en paralelo. Cada agente procesa la entrada de forma independiente y sus resultados se recopilan y agregan. Este enfoque es adecuado para escenarios en los que diversas perspectivas o soluciones son valiosas, como lluvia de ideas, razonamiento de conjuntos o sistemas de votación.

Para obtener más información sobre el patrón, como cuándo usar el patrón o cuándo evitar el patrón, consulte Orquestación simultánea.

Casos de uso comunes

Varios agentes generan diferentes soluciones a un problema y sus respuestas se recopilan para un análisis o selección adicionales:

Temas que se abordarán

• Cómo definir varios agentes con diferentes conocimientos
• Cómo organizar estos agentes para que funcionen simultáneamente en una sola tarea
• Recopilación y procesamiento de los resultados

using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Agents;
using Microsoft.SemanticKernel.Agents.Orchestration;
using Microsoft.SemanticKernel.Agents.Orchestration.Concurrent;
using Microsoft.SemanticKernel.Agents.Runtime.InProcess;

// Create a kernel with an AI service
Kernel kernel = ...;

ChatCompletionAgent physicist = new ChatCompletionAgent{
    Name = "PhysicsExpert",
    Instructions = "You are an expert in physics. You answer questions from a physics perspective."
    Kernel = kernel,
};

ChatCompletionAgent chemist = new ChatCompletionAgent{
    Name = "ChemistryExpert",
    Instructions = "You are an expert in chemistry. You answer questions from a chemistry perspective."
    Kernel = kernel,
};

ConcurrentOrchestration orchestration = new (physicist, chemist);

InProcessRuntime runtime = new InProcessRuntime();
await runtime.StartAsync();

var result = await orchestration.InvokeAsync("What is temperature?", runtime);

string[] output = await result.GetValueAsync(TimeSpan.FromSeconds(20));
Console.WriteLine($"# RESULT:\n{string.Join("\n\n", output.Select(text => $"{text}"))}");

await runtime.RunUntilIdleAsync();

# RESULT:
Temperature is a fundamental physical quantity that measures the average kinetic energy ...

Temperature is a measure of the average kinetic energy of the particles ...

from semantic_kernel.agents import Agent, ChatCompletionAgent
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion

def get_agents() -> list[Agent]:
    physics_agent = ChatCompletionAgent(
        name="PhysicsExpert",
        instructions="You are an expert in physics. You answer questions from a physics perspective.",
        service=AzureChatCompletion(),
    )
    chemistry_agent = ChatCompletionAgent(
        name="ChemistryExpert",
        instructions="You are an expert in chemistry. You answer questions from a chemistry perspective.",
        service=AzureChatCompletion(),
    )
    return [physics_agent, chemistry_agent]

from semantic_kernel.agents import ConcurrentOrchestration

agents = get_agents()
concurrent_orchestration = ConcurrentOrchestration(members=agents)

from semantic_kernel.agents.runtime import InProcessRuntime

runtime = InProcessRuntime()
runtime.start()

orchestration_result = await concurrent_orchestration.invoke(
    task="What is temperature?",
    runtime=runtime,
)

value = await orchestration_result.get(timeout=20)
# For the concurrent orchestration, the result is a list of chat messages
for item in value:
    print(f"# {item.name}: {item.content}")

await runtime.stop_when_idle()

# PhysicsExpert: Temperature is a physical quantity that represents the average kinetic energy of the particles in a substance...
# ChemistryExpert: Temperature is a fundamental concept in chemistry and physics, representing a measure of the average kinetic energy...

Pasos siguientes