Orquestração de Entrega

Definir agentes especializados

Cada agente é responsável por uma área específica. Neste exemplo, definimos um agente de triagem, um agente de reembolso, um agente de status do pedido e um agente de retorno de pedidos. Alguns agentes usam plug-ins para lidar com tarefas específicas.

using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Agents;
using Microsoft.SemanticKernel.Agents.Orchestration;
using Microsoft.SemanticKernel.Agents.Orchestration.Handoff;
using Microsoft.SemanticKernel.Agents.Runtime.InProcess;
using Microsoft.SemanticKernel.ChatCompletion;

// Plugin implementations
public sealed class OrderStatusPlugin {
    [KernelFunction]
    public string CheckOrderStatus(string orderId) => $"Order {orderId} is shipped and will arrive in 2-3 days.";
}
public sealed class OrderReturnPlugin {
    [KernelFunction]
    public string ProcessReturn(string orderId, string reason) => $"Return for order {orderId} has been processed successfully.";
}
public sealed class OrderRefundPlugin {
    [KernelFunction]
    public string ProcessReturn(string orderId, string reason) => $"Refund for order {orderId} has been processed successfully.";
}

// Helper function to create a kernel with chat completion
public static Kernel CreateKernelWithChatCompletion(...)
{
    ...
}

ChatCompletionAgent triageAgent = new ChatCompletionAgent {
    Name = "TriageAgent",
    Description = "Handle customer requests.",
    Instructions = "A customer support agent that triages issues.",
    Kernel = CreateKernelWithChatCompletion(...),
};

ChatCompletionAgent statusAgent = new ChatCompletionAgent {
    Name = "OrderStatusAgent",
    Description = "A customer support agent that checks order status.",
    Instructions = "Handle order status requests.",
    Kernel = CreateKernelWithChatCompletion(...),
};
statusAgent.Kernel.Plugins.Add(KernelPluginFactory.CreateFromObject(new OrderStatusPlugin()));

ChatCompletionAgent returnAgent = new ChatCompletionAgent {
    Name = "OrderReturnAgent",
    Description = "A customer support agent that handles order returns.",
    Instructions = "Handle order return requests.",
    Kernel = CreateKernelWithChatCompletion(...),
};
returnAgent.Kernel.Plugins.Add(KernelPluginFactory.CreateFromObject(new OrderReturnPlugin()));

ChatCompletionAgent refundAgent = new ChatCompletionAgent {
    Name = "OrderRefundAgent",
    Description = "A customer support agent that handles order refund.",
    Instructions = "Handle order refund requests.",
    Kernel = CreateKernelWithChatCompletion(...),
};
refundAgent.Kernel.Plugins.Add(KernelPluginFactory.CreateFromObject(new OrderRefundPlugin()));

Configurar relações de entrega

Use OrchestrationHandoffs para especificar qual agente pode entregar para qual e em quais circunstâncias.

var handoffs = OrchestrationHandoffs
    .StartWith(triageAgent)
    .Add(triageAgent, statusAgent, returnAgent, refundAgent)
    .Add(statusAgent, triageAgent, "Transfer to this agent if the issue is not status related")
    .Add(returnAgent, triageAgent, "Transfer to this agent if the issue is not return related")
    .Add(refundAgent, triageAgent, "Transfer to this agent if the issue is not refund related");

Observar respostas do agente

Você pode criar um retorno de chamada por meio da propriedade ResponseCallback para capturar respostas do agente conforme a conversa progride.

ChatHistory history = [];

ValueTask responseCallback(ChatMessageContent response)
{
    history.Add(response);
    return ValueTask.CompletedTask;
}

Humano no Loop

Um recurso fundamental da orquestração de entrega é a capacidade de um humano participar da conversa. Isso é feito fornecendo um InteractiveCallback, que é chamado sempre que um agente precisa de entrada do usuário. Em um aplicativo real, isso solicitaria entrada ao usuário; em um exemplo, você pode usar uma fila de respostas.

// Simulate user input with a queue
Queue<string> responses = new();
responses.Enqueue("I'd like to track the status of my order");
responses.Enqueue("My order ID is 123");
responses.Enqueue("I want to return another order of mine");
responses.Enqueue("Order ID 321");
responses.Enqueue("Broken item");
responses.Enqueue("No, bye");

ValueTask<ChatMessageContent> interactiveCallback()
{
    string input = responses.Dequeue();
    Console.WriteLine($"\n# INPUT: {input}\n");
    return ValueTask.FromResult(new ChatMessageContent(AuthorRole.User, input));
}

Configurar a orquestração de entrega

Crie um objeto HandoffOrchestration, passando os agentes, as relações de transferência e os retornos de chamada.

HandoffOrchestration orchestration = new HandoffOrchestration(
    handoffs,
    triageAgent,
    statusAgent,
    returnAgent,
    refundAgent)
{
    InteractiveCallback = interactiveCallback,
    ResponseCallback = responseCallback,
};

Iniciar o Runtime

Um runtime é necessário para gerenciar a execução de agentes. Aqui, usamos InProcessRuntime e o iniciamos previamente à invocação da orquestração.

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

Invocar a Orquestração

Invoque a orquestração com sua tarefa inicial (por exemplo, "Sou um cliente que precisa de ajuda com meus pedidos"). Os agentes rotearão a conversa conforme necessário, envolvendo o humano quando necessário.

string task = "I am a customer that needs help with my orders";
var result = await orchestration.InvokeAsync(task, runtime);

Coletar Resultados

Aguarde até que a orquestração seja concluída e recupere o resultado final.

string output = await result.GetValueAsync(TimeSpan.FromSeconds(300));
Console.WriteLine($"\n# RESULT: {output}");
Console.WriteLine("\n\nORCHESTRATION HISTORY");
foreach (ChatMessageContent message in history)
{
    // Print each message
    Console.WriteLine($"# {message.Role} - {message.AuthorName}: {message.Content}");
}

Opcional: interromper o runtime

Após a conclusão do processamento, interrompa o runtime para limpar os recursos.

await runtime.RunUntilIdleAsync();

Saída de exemplo

# RESULT: Handled order return for order ID 321 due to a broken item, and successfully processed the return.

ORCHESTRATION HISTORY

# Assistant - TriageAgent: Could you please specify what kind of help you need with your orders? Are you looking to check the order status, return an item, or request a refund?

# Assistant - OrderStatusAgent: Could you please tell me your order ID?

# Assistant - OrderStatusAgent: Your order with ID 123 has been shipped and will arrive in 2-3 days. Anything else I can assist you with?

# Assistant - OrderReturnAgent: I can help you with that. Could you please provide the order ID and the reason you'd like to return it?

# Assistant - OrderReturnAgent: Please provide the reason for returning the order with ID 321.

# Assistant - OrderReturnAgent: The return for your order with ID 321 has been successfully processed due to the broken item. Anything else I can assist you with?

Definir agentes especializados

Cada agente é responsável por uma área específica. Por exemplo:

• TriageAgent: lida com as solicitações iniciais do cliente e decide qual especialista envolver.
• RefundAgent: manipula solicitações de reembolso.
• OrderStatusAgent: verifica o status do pedido.
• OrderReturnAgent: gerencia o retorno de pedidos.

Plug-ins

Primeiro, precisamos definir os plug-ins que serão usados nos agentes. Esses plug-ins conterão a lógica para lidar com tarefas específicas.

from semantic_kernel.functions import kernel_function

class OrderStatusPlugin:
    @kernel_function
    def check_order_status(self, order_id: str) -> str:
        """Check the status of an order."""
        # Simulate checking the order status
        return f"Order {order_id} is shipped and will arrive in 2-3 days."


class OrderRefundPlugin:
    @kernel_function
    def process_refund(self, order_id: str, reason: str) -> str:
        """Process a refund for an order."""
        # Simulate processing a refund
        print(f"Processing refund for order {order_id} due to: {reason}")
        return f"Refund for order {order_id} has been processed successfully."


class OrderReturnPlugin:
    @kernel_function
    def process_return(self, order_id: str, reason: str) -> str:
        """Process a return for an order."""
        # Simulate processing a return
        print(f"Processing return for order {order_id} due to: {reason}")
        return f"Return for order {order_id} has been processed successfully."

Agentes

Em seguida, definimos os agentes que usarão esses plug-ins.

from semantic_kernel.agents import ChatCompletionAgent
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion

support_agent = ChatCompletionAgent(
    name="TriageAgent",
    description="A customer support agent that triages issues.",
    instructions="Handle customer requests.",
    service=OpenAIChatCompletion(),
)

refund_agent = ChatCompletionAgent(
    name="RefundAgent",
    description="A customer support agent that handles refunds.",
    instructions="Handle refund requests.",
    service=OpenAIChatCompletion(),
    plugins=[OrderRefundPlugin()],
)

order_status_agent = ChatCompletionAgent(
    name="OrderStatusAgent",
    description="A customer support agent that checks order status.",
    instructions="Handle order status requests.",
    service=OpenAIChatCompletion(),
    plugins=[OrderStatusPlugin()],
)

order_return_agent = ChatCompletionAgent(
    name="OrderReturnAgent",
    description="A customer support agent that handles order returns.",
    instructions="Handle order return requests.",
    service=OpenAIChatCompletion(),
    plugins=[OrderReturnPlugin()],
)

Definir relações de transferência

Use OrchestrationHandoffs para especificar qual agente pode entregar para qual e em quais circunstâncias.

from semantic_kernel.agents import OrchestrationHandoffs

handoffs = (
    OrchestrationHandoffs()
    .add_many(    # Use add_many to add multiple handoffs to the same source agent at once
        source_agent=support_agent.name,
        target_agents={
            refund_agent.name: "Transfer to this agent if the issue is refund related",
            order_status_agent.name: "Transfer to this agent if the issue is order status related",
            order_return_agent.name: "Transfer to this agent if the issue is order return related",
        },
    )
    .add(    # Use add to add a single handoff
        source_agent=refund_agent.name,
        target_agent=support_agent.name,
        description="Transfer to this agent if the issue is not refund related",
    )
    .add(
        source_agent=order_status_agent.name,
        target_agent=support_agent.name,
        description="Transfer to this agent if the issue is not order status related",
    )
    .add(
        source_agent=order_return_agent.name,
        target_agent=support_agent.name,
        description="Transfer to this agent if the issue is not order return related",
    )
)

Observar respostas do agente

Você pode definir um retorno de chamada para imprimir a mensagem de cada agente à medida que a conversa progride.

from semantic_kernel.contents import ChatMessageContent

def agent_response_callback(message: ChatMessageContent) -> None:
    print(f"{message.name}: {message.content}")

Humano no Loop

Um recurso fundamental da orquestração de entrega é a capacidade de um humano participar da conversa. Isso é feito fornecendo um human_response_function callback, que é acionado sempre que um agente precisa de informações do usuário.

from semantic_kernel.contents import AuthorRole, ChatMessageContent

def human_response_function() -> ChatMessageContent:
    user_input = input("User: ")
    return ChatMessageContent(role=AuthorRole.USER, content=user_input)

Configurar a orquestração de entrega

Crie um objeto HandoffOrchestration, passando os agentes, as relações de transferência e os retornos de chamada.

from semantic_kernel.agents import HandoffOrchestration

handoff_orchestration = HandoffOrchestration(
    members=[
        support_agent,
        refund_agent,
        order_status_agent,
        order_return_agent,
    ],
    handoffs=handoffs,
    agent_response_callback=agent_response_callback,
    human_response_function=human_response_function,
)

Iniciar o Runtime

Inicie o runtime para gerenciar a execução do agente.

from semantic_kernel.agents.runtime import InProcessRuntime

runtime = InProcessRuntime()
runtime.start()

Invocar a Orquestração

Invoque a orquestração com sua tarefa inicial (por exemplo, "Um cliente está na linha"). Os agentes rotearão a conversa conforme necessário, envolvendo o humano quando necessário.

orchestration_result = await handoff_orchestration.invoke(
    task="A customer is on the line.",
    runtime=runtime,
)

Coletar Resultados

Aguarde a conclusão da orquestração.

value = await orchestration_result.get()
print(value)

Opcional: interromper o runtime

Após a conclusão do processamento, interrompa o runtime para limpar os recursos.

await runtime.stop_when_idle()

Saída de exemplo

TriageAgent: Hello! Thank you for reaching out. How can I assist you today?
User: I'd like to track the status of my order
OrderStatusAgent: Sure, I can help you with that. Could you please provide me with your order ID?
User: My order ID is 123
OrderStatusAgent: Your order with ID 123 has been shipped and is expected to arrive in 2-3 days. Is there anything else I can assist you with?
User: I want to return another order of mine
OrderReturnAgent: I can help you with returning your order. Could you please provide the order ID for the return and the reason you'd like to return it?
User: Order ID 321
OrderReturnAgent: Please provide the reason for returning the order with ID 321.
User: Broken item
OrderReturnAgent: The return for your order with ID 321 has been successfully processed due to the broken item. Is there anything else I can assist you with?
User: No, bye
Task is completed with summary: Handled order return for order ID 321 due to a broken item, and successfully processed the return.