OpenAI 代理

入门

将所需的 NuGet 包添加到项目。

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

Responses 客户端

响应客户端是推荐的主要客户端，提供最丰富的工具支持，包括代码解释器、文件搜索、Web 搜索和托管 MCP。

using Microsoft.Agents.AI;
using OpenAI;

OpenAIClient client = new OpenAIClient("<your_api_key>");
var responsesClient = client.GetResponsesClient();

AIAgent agent = responsesClient.AsAIAgent(
    model: "gpt-4o-mini",
    instructions: "You are a helpful coding assistant.",
    name: "CodeHelper");

Console.WriteLine(await agent.RunAsync("Write a Python function to sort a list."));

支持的工具： 函数工具、工具审批、代码解释器、文件搜索、Web 搜索、托管 MCP、本地 MCP 工具。

Chat Completion 客户端

聊天完成客户端提供了使用聊天完成 API 创建代理的简单方法。 如果需要广泛的模型兼容性或者有现有的 Chat Completions 集成，使用它。

using Microsoft.Agents.AI;
using OpenAI;

OpenAIClient client = new OpenAIClient("<your_api_key>");
var chatClient = client.GetChatClient("gpt-4o-mini");

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

Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));

支持的工具： 函数工具、Web 搜索、本地 MCP 工具。

助手客户端

使用代理

这两种客户端类型都生成支持相同代理操作（流式处理、线程、中间件）的标准 AIAgent 。

有关详细信息，请参阅 入门教程。

工具

OpenAI .NET客户端根据它们所面向的 API 公开不同的工具图面。 相同的对应矩阵也适用于 Azure OpenAI 提供程序页 上对应的 Azure OpenAI 客户端。

安装

pip install agent-framework-openai

agent-framework-openai 是用于直接 OpenAI 和 Azure OpenAI 用法的可选 Python 提供程序包。

配置

Python OpenAI 聊天客户端使用以下环境变量模式：

OPENAI_API_KEY="your-openai-api-key"
OPENAI_CHAT_MODEL="gpt-4o-mini"
# Optional shared fallback:
# OPENAI_MODEL="gpt-4o-mini"

OPENAI_API_KEY="your-openai-api-key"
OPENAI_CHAT_COMPLETION_MODEL="gpt-4o-mini"
# Optional shared fallback:
# OPENAI_MODEL="gpt-4o-mini"

AZURE_OPENAI_ENDPOINT="https://<resource>.openai.azure.com"
AZURE_OPENAI_CHAT_MODEL="gpt-4o-mini"
# Optional shared fallback:
# AZURE_OPENAI_MODEL="gpt-4o-mini"
AZURE_OPENAI_API_VERSION="your-api-version"

import asyncio
import os
from agent_framework.openai import OpenAIChatClient
from azure.identity import AzureCliCredential

async def main():
    agent = OpenAIChatClient(
        model=os.environ["AZURE_OPENAI_CHAT_MODEL"],
        azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
        api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
        credential=AzureCliCredential(),
    ).as_agent(
        name="AzureOpenAIResponsesAgent",
        instructions="You are a helpful assistant.",
    )

    result = await agent.run("Hello!")
    print(result)

asyncio.run(main())

import os
from agent_framework.openai import OpenAIEmbeddingClient
from azure.identity import AzureCliCredential

client = OpenAIEmbeddingClient(
    model=os.environ["AZURE_OPENAI_EMBEDDING_MODEL"],
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
    credential=AzureCliCredential(),
)

import asyncio
from agent_framework.openai import OpenAIChatClient

async def main():
    agent = OpenAIChatClient().as_agent(
        name="FullFeaturedAgent",
        instructions="You are a helpful assistant with access to many tools.",
    )
    result = await agent.run("Write and run a Python script that calculates fibonacci numbers.")
    print(result)

asyncio.run(main())

async def hosted_tools_example():
    client = OpenAIChatClient()

    # Each tool is created via a client method
    code_interpreter = client.get_code_interpreter_tool()
    web_search = client.get_web_search_tool()
    file_search = client.get_file_search_tool(vector_store_ids=["vs_abc123"])
    mcp_tool = client.get_mcp_tool(
        name="GitHub",
        url="https://api.githubcopilot.com/mcp/",
        approval_mode="never_require",
    )

    agent = client.as_agent(
        name="PowerAgent",
        instructions="You have access to code execution, web search, files, and GitHub.",
        tools=[code_interpreter, web_search, file_search, mcp_tool],
    )
    result = await agent.run("Search the web for Python best practices, then write a summary.")
    print(result)

import asyncio
from agent_framework.openai import OpenAIChatCompletionClient

async def main():
    agent = OpenAIChatCompletionClient().as_agent(
        name="HelpfulAssistant",
        instructions="You are a helpful assistant.",
    )
    result = await agent.run("Hello, how can you help me?")
    print(result)

asyncio.run(main())

async def web_search_example():
    client = OpenAIChatCompletionClient()
    web_search = client.get_web_search_tool()

    agent = client.as_agent(
        name="SearchBot",
        instructions="You can search the web for current information.",
        tools=web_search,
    )
    result = await agent.run("What are the latest developments in AI?")
    print(result)

常见功能

这些客户端类型支持以下标准代理功能：

函数工具

from agent_framework import tool

@tool
def get_weather(location: str) -> str:
    """Get the weather for a given location."""
    return f"The weather in {location} is sunny, 25°C."

async def example():
    agent = OpenAIChatClient().as_agent(
        instructions="You are a weather assistant.",
        tools=get_weather,
    )
    result = await agent.run("What's the weather in Tokyo?")
    print(result)

多回合对话

async def thread_example():
    agent = OpenAIChatClient().as_agent(
        instructions="You are a helpful assistant.",
    )
    session = agent.create_session()

    result1 = await agent.run("My name is Alice", session=session)
    print(result1)
    result2 = await agent.run("What's my name?", session=session)
    print(result2)  # Remembers "Alice"

流媒体

async def streaming_example():
    agent = OpenAIChatClient().as_agent(
        instructions="You are a creative storyteller.",
    )
    print("Agent: ", end="", flush=True)
    async for chunk in agent.run("Tell me a short story about AI.", stream=True):
        if chunk.text:
            print(chunk.text, end="", flush=True)
    print()

使用代理

所有客户端类型都生成支持相同操作的标准 Agent。

有关详细信息，请参阅 入门教程。

工具

Python OpenAI 客户端根据基础 API 公开不同的工具图面。 OpenAIChatClient (Responses) 通过 client.get_*_tool(...) 提供托管工具工厂 — get_code_interpreter_tool、get_file_search_tool、get_web_search_tool、get_image_generation_tool、get_shell_tool 和 get_mcp_tool。 OpenAIChatCompletionClient 只暴露 get_web_search_tool。 两者都可与函数工具和本地 MCP 服务器配合使用。

将这些客户端指向 Azure OpenAI 时，将应用相同的矩阵 — 请参阅 Azure OpenAI。

OpenAI 聊天补全

该 openaiprovider 包使用 OpenAI 聊天完成 API 创建代理。

安装

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

Direct OpenAI

import (
    "github.com/microsoft/agent-framework-go/agent"
    "github.com/microsoft/agent-framework-go/provider/openaiprovider"

    "github.com/openai/openai-go/v3"
)

a := openaiprovider.NewChatCompletionsAgent(
    openai.NewClient(), // uses OPENAI_API_KEY env var
    openaiprovider.AgentConfig{
        Model: "gpt-4o-mini",
        Instructions: "You are a helpful assistant.",
        Config: agent.Config{
            Name:         "MyAgent",
        },
    },
)

resp, err := a.RunText(ctx, "Tell me a joke.").Collect()

Azure OpenAI

使用相同的 openaiprovider 包和 Azure 凭据：

import (
    "github.com/Azure/azure-sdk-for-go/sdk/azidentity"
    openai "github.com/openai/openai-go/v3"
    "github.com/openai/openai-go/v3/azure"
)

token, _ := azidentity.NewDefaultAzureCredential(nil)

a := openaiprovider.NewChatCompletionsAgent(
    openai.NewClient(
        azure.WithEndpoint(endpoint, apiVersion),
        azure.WithTokenCredential(token),
    ),
    openaiprovider.AgentConfig{
        Model: deployment,
        Instructions: "You are a helpful assistant.",
        Config: agent.Config{
        },
    },
)

自定义选项

使用 openaiprovider.ChatCompletionNewParams 传递特定于提供程序的选项：

resp, err := a.RunText(ctx, "Hello!",
    openaiprovider.ChatCompletionNewParams(openai.ChatCompletionNewParams{
        Temperature: openai.Float(0.7),
    }),
).Collect()

支持的工具： 函数工具、Web 搜索、本地 MCP 工具。