Azure OpenAI ChatCompletion 代理

入门

将所需的 NuGet 包添加到项目。

dotnet add package Azure.AI.OpenAI --prerelease
dotnet add package Azure.Identity
dotnet add package Microsoft.Agents.AI.OpenAI --prerelease

创建 Azure OpenAI ChatCompletion 代理

首先需要创建客户端以连接到 Azure OpenAI 服务。

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

AzureOpenAIClient client = new AzureOpenAIClient(
    new Uri("https://<myresource>.openai.azure.com"),
    new AzureCliCredential());

Azure OpenAI 支持多个服务，这些服务都提供模型调用功能。 我们需要选择 ChatCompletion 服务来创建基于 ChatCompletion 的代理。

var chatCompletionClient = client.GetChatClient("gpt-4o-mini");

最后，使用 CreateAIAgent 扩展方法在 ChatCompletionClient 上创建代理。

AIAgent agent = chatCompletionClient.CreateAIAgent(
    instructions: "You are good at telling jokes.",
    name: "Joker");
// Invoke the agent and output the text result.
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));

代理功能

函数工具

可以向 Azure OpenAI ChatCompletion 代理提供自定义函数工具：

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

var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";

[Description("Get the weather for a given location.")]
static string GetWeather([Description("The location to get the weather for.")] string location)
    => $"The weather in {location} is cloudy with a high of 15°C.";

// Create the chat client and agent, and provide the function tool to the agent.
AIAgent agent = new AzureOpenAIClient(
    new Uri(endpoint),
    new AzureCliCredential())
     .GetChatClient(deploymentName)
     .CreateAIAgent(instructions: "You are a helpful assistant", tools: [AIFunctionFactory.Create(GetWeather)]);

// Non-streaming agent interaction with function tools.
Console.WriteLine(await agent.RunAsync("What is the weather like in Amsterdam?"));

流式处理响应

使用流媒体生成时获取响应：

AIAgent agent = chatCompletionClient.CreateAIAgent(
    instructions: "You are good at telling jokes.",
    name: "Joker");

// Invoke the agent with streaming support.
await foreach (var update in agent.RunStreamingAsync("Tell me a joke about a pirate."))
{
    Console.Write(update);
}

使用代理

代理是标准的AIAgent，支持所有标准AIAgent操作。

有关如何运行和与代理交互的详细信息，请参阅 代理入门教程 。

配置

环境变量

在使用 Azure OpenAI ChatCompletion 代理之前，需要设置以下环境变量：

export AZURE_OPENAI_ENDPOINT="https://<myresource>.openai.azure.com"
export AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="gpt-4o-mini"

（可选）还可以设置：

export AZURE_OPENAI_API_VERSION="2024-10-21"  # Default API version
export AZURE_OPENAI_API_KEY="<your-api-key>"  # If not using Azure CLI authentication

Installation

将 Agent Framework 包添加到项目：

pip install agent-framework --pre

入门

Authentication

Azure OpenAI 代理使用 Azure 凭据进行身份验证。 最简单的方法是在运行AzureCliCredential后使用az login：

from azure.identity import AzureCliCredential

credential = AzureCliCredential()

创建 Azure OpenAI ChatCompletion 代理

基本代理创建

创建代理的最简单方法是使用 AzureOpenAIChatClient 和环境变量：

import asyncio
from agent_framework.azure import AzureOpenAIChatClient
from azure.identity import AzureCliCredential

async def main():
    agent = AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
        instructions="You are good at telling jokes.",
        name="Joker"
    )

    result = await agent.run("Tell me a joke about a pirate.")
    print(result.text)

asyncio.run(main())

显式配置

还可以显式提供配置，而不是使用环境变量：

import asyncio
from agent_framework.azure import AzureOpenAIChatClient
from azure.identity import AzureCliCredential

async def main():
    agent = AzureOpenAIChatClient(
        endpoint="https://<myresource>.openai.azure.com",
        deployment_name="gpt-4o-mini",
        credential=AzureCliCredential()
    ).create_agent(
        instructions="You are good at telling jokes.",
        name="Joker"
    )

    result = await agent.run("Tell me a joke about a pirate.")
    print(result.text)

asyncio.run(main())

代理功能

函数工具

可以向 Azure OpenAI ChatCompletion 代理提供自定义函数工具：

import asyncio
from typing import Annotated
from agent_framework.azure import AzureOpenAIChatClient
from azure.identity import AzureCliCredential
from pydantic import Field

def get_weather(
    location: Annotated[str, Field(description="The location to get the weather for.")],
) -> str:
    """Get the weather for a given location."""
    return f"The weather in {location} is sunny with a high of 25°C."

async def main():
    agent = AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
        instructions="You are a helpful weather assistant.",
        tools=get_weather
    )

    result = await agent.run("What's the weather like in Seattle?")
    print(result.text)

asyncio.run(main())

流式处理响应

使用流式处理生成时立即获取响应：

import asyncio
from agent_framework.azure import AzureOpenAIChatClient
from azure.identity import AzureCliCredential

async def main():
    agent = AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
        instructions="You are a helpful assistant."
    )

    print("Agent: ", end="", flush=True)
    async for chunk in agent.run_stream("Tell me a short story about a robot"):
        if chunk.text:
            print(chunk.text, end="", flush=True)
    print()

asyncio.run(main())

使用代理

代理是标准 BaseAgent 代理，支持所有标准代理操作。

有关如何运行和与代理交互的详细信息，请参阅 代理入门教程 。