Inicio rápido: Compilación de agentes mediante la API de respuestas

• Python 3.10 o posterior instalado.

• Tener instalado el SDK de .NET 8 o una versión posterior.

pip install agent-framework-foundry aiohttp

dotnet add package Microsoft.Agents.AI.Foundry --prerelease
dotnet add package Azure.AI.Projects --prerelease
dotnet add package Azure.Identity

Microsoft.Agents.AI.Foundry proporciona el método de extensión AsAIAgent(...) en AIProjectClient y trae de forma transitiva Microsoft.Agents.AI.

Use FoundryChatClient y la clase Agent.

import asyncio
import os

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=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
            model=os.environ["FOUNDRY_MODEL"],
            credential=AzureCliCredential(),
        ),
        instructions="You are a helpful assistant.",
    )

    result = await agent.run("What is the capital of France?")
    print(f"Agent: {result}")

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

El resultado muestra la respuesta del agente. Dado que el agente es efímero, no se conserva ninguna definición en el servicio; solo existe durante la vigencia del proceso de Python.

Utilice AIProjectClient.AsAIAgent(...) del Microsoft Agent Framework para encapsular el punto de conexión del proyecto de Foundry como un AIAgent.

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

string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT")
    ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL")
    ?? throw new InvalidOperationException("FOUNDRY_MODEL is not set.");

AIAgent agent =
    new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
    .AsAIAgent(
        model: deploymentName,
        instructions: "You are a helpful assistant.",
        name: "Assistant");

Console.WriteLine($"Agent: {await agent.RunAsync("What is the capital of France?")}");

La salida muestra la respuesta del agente. Dado que el agente es efímero, no se conserva ninguna definición en el servicio, solo existe durante la vigencia del proceso.

Defina las herramientas de función locales mediante el @tool decorador.

import asyncio
import os
from random import randint
from typing import Annotated

from agent_framework import Agent, tool
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from pydantic import Field

@tool(approval_mode="never_require")
def get_weather(
    location: Annotated[str, Field(description="The location to get the weather for.")],
) -> str:
    """Get the weather for a given location."""
    conditions = ["sunny", "cloudy", "rainy", "stormy"]
    return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."

async def main() -> None:
    agent = Agent(
        client=FoundryChatClient(
            project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
            model=os.environ["FOUNDRY_MODEL"],
            credential=AzureCliCredential(),
        ),
        instructions="You are a helpful weather agent.",
        tools=get_weather,
    )

    result = await agent.run("What's the weather like in Seattle?")
    print(f"Agent: {result}")

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

El agente usa la API de respuestas para determinar cuándo llamar a la get_weather función, la ejecuta localmente y devuelve el resultado en lenguaje natural.

Defina un método local, decórelo con atributos [Description] y envuélvalo con AIFunctionFactory.Create(...).

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

[Description("Get the weather for a given location.")]
static string GetWeather(
    [Description("The location to get the weather for.")] string location)
{
    string[] conditions = ["sunny", "cloudy", "rainy", "stormy"];
    Random rng = Random.Shared;
    return $"The weather in {location} is {conditions[rng.Next(conditions.Length)]} with a high of {rng.Next(10, 31)}°C.";
}

AITool weatherTool = AIFunctionFactory.Create(GetWeather);

string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT")
    ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL")
    ?? throw new InvalidOperationException("FOUNDRY_MODEL is not set.");

AIAgent agent =
    new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
    .AsAIAgent(
        model: deploymentName,
        instructions: "You are a helpful weather agent.",
        name: "WeatherAssistant",
        tools: [weatherTool]);

Console.WriteLine($"Agent: {await agent.RunAsync("What's the weather like in Seattle?")}");

El agente usa la API de Responses para determinar cuándo llamar a GetWeather, la ejecuta localmente y devuelve el resultado en lenguaje natural.

Utilice FoundryChatClient.get_web_search_tool():

import asyncio
import os

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=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
            model=os.environ["FOUNDRY_MODEL"],
            credential=AzureCliCredential(),
        ),
        instructions="You are a research assistant. Use web search to find current information.",
        tools=[
            FoundryChatClient.get_web_search_tool(),
        ],
    )

    result = await agent.run("What are the latest updates to Microsoft Foundry?")
    print(f"Agent: {result}")

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

La herramienta de búsqueda en la web se ejecuta en el servidor a través de la API de respuestas del proyecto Foundry. Puede combinarlo con herramientas de funciones locales para proporcionar al agente acceso web y funcionalidades de código personalizadas:

agent = Agent(
    client=FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
        model=os.environ["FOUNDRY_MODEL"],
        credential=AzureCliCredential(),
    ),
    instructions="You are a helpful assistant with web and weather capabilities.",
    tools=[
        FoundryChatClient.get_web_search_tool(),
        get_weather,  # Local function tool defined with @tool
    ],
)

Pase new HostedWebSearchTool() en la lista tools:

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

string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT")
    ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL")
    ?? throw new InvalidOperationException("FOUNDRY_MODEL is not set.");

AIAgent agent =
    new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
    .AsAIAgent(
        model: deploymentName,
        instructions: "You are a research assistant. Use web search to find current information.",
        name: "ResearchAssistant",
        tools: [new HostedWebSearchTool()]);

Console.WriteLine($"Agent: {await agent.RunAsync("What are the latest updates to Microsoft Foundry?")}");

La herramienta de búsqueda web se ejecuta del lado del servidor a través de la API de Responses del proyecto Foundry. Puede combinarlo con herramientas de funciones locales para proporcionar al agente acceso web y funcionalidades de código personalizadas:

AIAgent agent =
    new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
    .AsAIAgent(
        model: deploymentName,
        instructions: "You are a helpful assistant with web and weather capabilities.",
        name: "Assistant",
        tools: [new HostedWebSearchTool(), weatherTool]);

Use el stream=True parámetro :

import asyncio
import os

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=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
            model=os.environ["FOUNDRY_MODEL"],
            credential=AzureCliCredential(),
        ),
        instructions="You are a helpful assistant.",
    )

    print("Agent: ", end="", flush=True)
    async for chunk in agent.run("Tell me a fun fact.", stream=True):
        if chunk.text:
            print(chunk.text, end="", flush=True)
    print()

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

Llame a RunStreamingAsync e itere el flujo AgentResponseUpdate:

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

string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT")
    ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL")
    ?? throw new InvalidOperationException("FOUNDRY_MODEL is not set.");

AIAgent agent =
    new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
    .AsAIAgent(
        model: deploymentName,
        instructions: "You are a helpful assistant.",
        name: "Assistant");

Console.Write("Agent: ");
await foreach (AgentResponseUpdate update in agent.RunStreamingAsync("Tell me a fun fact."))
{
    Console.Write(update);
}
Console.WriteLine();

• Ejemplos de proveedor de Foundry (Python)
• Ejemplos de API de respuestas del proyectoFoundry (SDK de OpenAI)

• Agentes con ejemplos de Foundry (.NET)