Início Rápido: Criar agentes usando a API de Respostas

• Python 3.10 ou posterior instalado.

• .NET 8 SDK ou versão posterior instalado.

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 fornece o método de extensão AsAIAgent(...) em AIProjectClient e traz Microsoft.Agents.AI transitivamente.

Use FoundryChatClient e a classe 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())

A saída exibe a resposta do agente. Como o agente é efêmero, nenhuma definição é persistida no serviço — ela existe apenas durante o ciclo de vida do processo Python.

Use AIProjectClient.AsAIAgent(...) da Microsoft Agent Framework para encapsular o endpoint do projeto do Foundry como um 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?")}");

A saída exibe a resposta do agente. Como o agente é efêmero, nenhuma definição é persistida no serviço — ela existe apenas durante o tempo de vida do processo.

Defina as ferramentas de função local usando o @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())

O agente usa a API de Respostas para determinar quando chamar a get_weather função, executá-la localmente e retorna o resultado em linguagem natural.

Defina um método local, decore-o com [Description] atributos e embrulhe-o com 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?")}");

O agente usa a API de Respostas para determinar quando chamar GetWeather, executa-a localmente e retorna o resultado em linguagem natural.

Use 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())

A ferramenta de busca na Web é executada no servidor por meio da API de Respostas do projeto Foundry. Você pode combiná-lo com ferramentas de função locais para fornecer ao agente acesso à Web e recursos de código personalizado:

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
    ],
)

Passe new HostedWebSearchTool() na 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?")}");

A ferramenta de busca na Web é executada no servidor por meio da API Responses do projeto Foundry. Você pode combiná-lo com ferramentas de função locais para fornecer ao agente acesso à Web e recursos de código personalizado:

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 o stream=True parâmetro:

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())

Chame RunStreamingAsync e itere o fluxo 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();

• Exemplos de provedores do Foundry (Python)
• Exemplos da API Responses do projeto Foundry (SDK da OpenAI)

• Agentes com exemplos do Foundry (.NET)