Passaggio 1: Il primo agente

dotnet add package Microsoft.Agents.AI.Foundry --prerelease

Creare l'agente:

using System;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;

var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
    ?? throw new InvalidOperationException("Set AZURE_OPENAI_ENDPOINT");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";

AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
    .AsAIAgent(
        model: deploymentName,
        instructions: "You are a friendly assistant. Keep your answers brief.",
        name: "HelloAgent");

Eseguilo:

Console.WriteLine(await agent.RunAsync("What is the largest city in France?"));

In alternativa, trasmettere la risposta:

await foreach (var update in agent.RunStreamingAsync("Tell me a one-sentence fun fact."))
{
    Console.Write(update);
}

pip install agent-framework-foundry azure-identity

Il pacchetto agent-framework-foundry installa agent-framework-core con l'integrazione di Microsoft Foundry. Il agent-framework metapacchetto installa agent-framework-coreanche , insieme a molte altre integrazioni facoltative.

Accedi con il interfaccia della riga di comando di Azure eseguendo az login. Nell'esempio seguente, sostituire project_endpoint con l'endpoint del progetto Microsoft Foundry e model con il nome della distribuzione del modello.

Salvare l'esempio completo come hello_agent.py:

import asyncio

from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential


async def main() -> None:
    agent = Agent(
        client=FoundryChatClient(
            project_endpoint="https://your-account.services.ai.azure.com/api/projects/your-project",
            model="gpt-6-luna",
            credential=AzureCliCredential(),
        ),
        instructions="You are a friendly assistant. Keep your answers brief.",
    )
    print(await agent.run("What is the largest city of France?"))


if __name__ == "__main__":
    asyncio.run(main())

Esegui l'esempio:

python hello_agent.py

from dotenv import load_dotenv
load_dotenv()

go get github.com/microsoft/agent-framework-go

Creare l'agente:

package main

import (
    "context"
    "fmt"
    "os"

    "github.com/microsoft/agent-framework-go/agent"
    "github.com/microsoft/agent-framework-go/provider/foundryprovider"

    "github.com/Azure/azure-sdk-for-go/sdk/azidentity"
)

func main() {
    endpoint := os.Getenv("FOUNDRY_PROJECT_ENDPOINT")
    model := os.Getenv("FOUNDRY_MODEL")

    token, err := azidentity.NewDefaultAzureCredential(nil)
    if err != nil {
        panic(err)
    }

    a := foundryprovider.NewAgent(
        endpoint,
        token,
        foundryprovider.ModelDeployment(model),
        foundryprovider.AgentConfig{
            Instructions: "You are a friendly assistant. Keep your answers brief.",
            Config: agent.Config{
                Name: "HelloAgent",
            },
        },
    )

Eseguilo:

    ctx := context.Background()

    resp, err := a.RunText(ctx, "What is the largest city in France?").Collect()
    fmt.Println(resp, err)

In alternativa, trasmettere la risposta:

    for update, err := range a.RunText(ctx, "Tell me a one-sentence fun fact.", agent.Stream(true)) {
        if err != nil {
            panic(err)
        }
        fmt.Print(update)
    }
}