azure-ai-openai-dotnet

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Azure.AI.OpenAI (.NET)

Azure.AI.OpenAI(.NET)

Client library for Azure OpenAI Service providing access to OpenAI models including GPT-4, GPT-4o, embeddings, DALL-E, and Whisper.
面向Azure OpenAI服务的客户端库,可访问包括GPT-4、GPT-4o、嵌入、DALL-E和Whisper在内的OpenAI模型。

Installation

安装

bash
dotnet add package Azure.AI.OpenAI
bash
dotnet add package Azure.AI.OpenAI

For OpenAI (non-Azure) compatibility

为兼容OpenAI(非Azure版本)

dotnet add package OpenAI

**Current Version**: 2.1.0 (stable)
dotnet add package OpenAI

**当前版本**:2.1.0(稳定版)

Environment Variables

环境变量

bash
AZURE_OPENAI_ENDPOINT=https://<resource-name>.openai.azure.com
AZURE_OPENAI_API_KEY=<api-key>                    # For key-based auth
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-mini          # Your deployment name
bash
AZURE_OPENAI_ENDPOINT=https://<resource-name>.openai.azure.com
AZURE_OPENAI_API_KEY=<api-key>                    # 基于密钥的认证
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-mini          # 你的部署名称

Client Hierarchy

客户端层级结构

AzureOpenAIClient (top-level)
├── GetChatClient(deploymentName)      → ChatClient
├── GetEmbeddingClient(deploymentName) → EmbeddingClient
├── GetImageClient(deploymentName)     → ImageClient
├── GetAudioClient(deploymentName)     → AudioClient
└── GetAssistantClient()               → AssistantClient
AzureOpenAIClient (顶级)
├── GetChatClient(deploymentName)      → ChatClient
├── GetEmbeddingClient(deploymentName) → EmbeddingClient
├── GetImageClient(deploymentName)     → ImageClient
├── GetAudioClient(deploymentName)     → AudioClient
└── GetAssistantClient()               → AssistantClient

Authentication

认证方式

API Key Authentication

API密钥认证

csharp
using Azure;
using Azure.AI.OpenAI;

AzureOpenAIClient client = new(
    new Uri(Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")!),
    new AzureKeyCredential(Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY")!));
csharp
using Azure;
using Azure.AI.OpenAI;

AzureOpenAIClient client = new(
    new Uri(Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")!),
    new AzureKeyCredential(Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY")!));

Microsoft Entra ID (Recommended for Production)

Microsoft Entra ID(生产环境推荐)

csharp
using Azure.Identity;
using Azure.AI.OpenAI;

AzureOpenAIClient client = new(
    new Uri(Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")!),
    new DefaultAzureCredential());
csharp
using Azure.Identity;
using Azure.AI.OpenAI;

AzureOpenAIClient client = new(
    new Uri(Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")!),
    new DefaultAzureCredential());

Using OpenAI SDK Directly with Azure

直接使用OpenAI SDK对接Azure

csharp
using Azure.Identity;
using OpenAI;
using OpenAI.Chat;
using System.ClientModel.Primitives;

#pragma warning disable OPENAI001

BearerTokenPolicy tokenPolicy = new(
    new DefaultAzureCredential(),
    "https://cognitiveservices.azure.com/.default");

ChatClient client = new(
    model: "gpt-4o-mini",
    authenticationPolicy: tokenPolicy,
    options: new OpenAIClientOptions()
    {
        Endpoint = new Uri("https://YOUR-RESOURCE.openai.azure.com/openai/v1")
    });
csharp
using Azure.Identity;
using OpenAI;
using OpenAI.Chat;
using System.ClientModel.Primitives;

#pragma warning disable OPENAI001

BearerTokenPolicy tokenPolicy = new(
    new DefaultAzureCredential(),
    "https://cognitiveservices.azure.com/.default");

ChatClient client = new(
    model: "gpt-4o-mini",
    authenticationPolicy: tokenPolicy,
    options: new OpenAIClientOptions()
    {
        Endpoint = new Uri("https://YOUR-RESOURCE.openai.azure.com/openai/v1")
    });

Chat Completions

聊天补全

Basic Chat

基础聊天

csharp
using Azure.AI.OpenAI;
using OpenAI.Chat;

AzureOpenAIClient azureClient = new(
    new Uri(endpoint),
    new DefaultAzureCredential());

ChatClient chatClient = azureClient.GetChatClient("gpt-4o-mini");

ChatCompletion completion = chatClient.CompleteChat(
[
    new SystemChatMessage("You are a helpful assistant."),
    new UserChatMessage("What is Azure OpenAI?")
]);

Console.WriteLine(completion.Content[0].Text);
csharp
using Azure.AI.OpenAI;
using OpenAI.Chat;

AzureOpenAIClient azureClient = new(
    new Uri(endpoint),
    new DefaultAzureCredential());

ChatClient chatClient = azureClient.GetChatClient("gpt-4o-mini");

ChatCompletion completion = chatClient.CompleteChat(
[
    new SystemChatMessage("You are a helpful assistant."),
    new UserChatMessage("What is Azure OpenAI?")
]);

Console.WriteLine(completion.Content[0].Text);

Async Chat

异步聊天

csharp
ChatCompletion completion = await chatClient.CompleteChatAsync(
[
    new SystemChatMessage("You are a helpful assistant."),
    new UserChatMessage("Explain cloud computing in simple terms.")
]);

Console.WriteLine($"Response: {completion.Content[0].Text}");
Console.WriteLine($"Tokens used: {completion.Usage.TotalTokenCount}");
csharp
ChatCompletion completion = await chatClient.CompleteChatAsync(
[
    new SystemChatMessage("You are a helpful assistant."),
    new UserChatMessage("Explain cloud computing in simple terms.")
]);

Console.WriteLine($"Response: {completion.Content[0].Text}");
Console.WriteLine($"Tokens used: {completion.Usage.TotalTokenCount}");

Streaming Chat

流式聊天

csharp
await foreach (StreamingChatCompletionUpdate update 
    in chatClient.CompleteChatStreamingAsync(messages))
{
    if (update.ContentUpdate.Count > 0)
    {
        Console.Write(update.ContentUpdate[0].Text);
    }
}
csharp
await foreach (StreamingChatCompletionUpdate update 
    in chatClient.CompleteChatStreamingAsync(messages))
{
    if (update.ContentUpdate.Count > 0)
    {
        Console.Write(update.ContentUpdate[0].Text);
    }
}

Chat with Options

带配置项的聊天

csharp
ChatCompletionOptions options = new()
{
    MaxOutputTokenCount = 1000,
    Temperature = 0.7f,
    TopP = 0.95f,
    FrequencyPenalty = 0,
    PresencePenalty = 0
};

ChatCompletion completion = await chatClient.CompleteChatAsync(messages, options);
csharp
ChatCompletionOptions options = new()
{
    MaxOutputTokenCount = 1000,
    Temperature = 0.7f,
    TopP = 0.95f,
    FrequencyPenalty = 0,
    PresencePenalty = 0
};

ChatCompletion completion = await chatClient.CompleteChatAsync(messages, options);

Multi-turn Conversation

多轮对话

csharp
List<ChatMessage> messages = new()
{
    new SystemChatMessage("You are a helpful assistant."),
    new UserChatMessage("Hi, can you help me?"),
    new AssistantChatMessage("Of course! What do you need help with?"),
    new UserChatMessage("What's the capital of France?")
};

ChatCompletion completion = await chatClient.CompleteChatAsync(messages);
messages.Add(new AssistantChatMessage(completion.Content[0].Text));
csharp
List<ChatMessage> messages = new()
{
    new SystemChatMessage("You are a helpful assistant."),
    new UserChatMessage("Hi, can you help me?"),
    new AssistantChatMessage("Of course! What do you need help with?"),
    new UserChatMessage("What's the capital of France?")
};

ChatCompletion completion = await chatClient.CompleteChatAsync(messages);
messages.Add(new AssistantChatMessage(completion.Content[0].Text));

Structured Outputs (JSON Schema)

结构化输出(JSON Schema)

csharp
using System.Text.Json;

ChatCompletionOptions options = new()
{
    ResponseFormat = ChatResponseFormat.CreateJsonSchemaFormat(
        jsonSchemaFormatName: "math_reasoning",
        jsonSchema: BinaryData.FromBytes("""
            {
                "type": "object",
                "properties": {
                    "steps": {
                        "type": "array",
                        "items": {
                            "type": "object",
                            "properties": {
                                "explanation": { "type": "string" },
                                "output": { "type": "string" }
                            },
                            "required": ["explanation", "output"],
                            "additionalProperties": false
                        }
                    },
                    "final_answer": { "type": "string" }
                },
                "required": ["steps", "final_answer"],
                "additionalProperties": false
            }
            """u8.ToArray()),
        jsonSchemaIsStrict: true)
};

ChatCompletion completion = await chatClient.CompleteChatAsync(
    [new UserChatMessage("How can I solve 8x + 7 = -23?")],
    options);

using JsonDocument json = JsonDocument.Parse(completion.Content[0].Text);
Console.WriteLine($"Answer: {json.RootElement.GetProperty("final_answer")}");
csharp
using System.Text.Json;

ChatCompletionOptions options = new()
{
    ResponseFormat = ChatResponseFormat.CreateJsonSchemaFormat(
        jsonSchemaFormatName: "math_reasoning",
        jsonSchema: BinaryData.FromBytes("""
            {
                "type": "object",
                "properties": {
                    "steps": {
                        "type": "array",
                        "items": {
                            "type": "object",
                            "properties": {
                                "explanation": { "type": "string" },
                                "output": { "type": "string" }
                            },
                            "required": ["explanation", "output"],
                            "additionalProperties": false
                        }
                    },
                    "final_answer": { "type": "string" }
                },
                "required": ["steps", "final_answer"],
                "additionalProperties": false
            }
            """u8.ToArray()),
        jsonSchemaIsStrict: true)
};

ChatCompletion completion = await chatClient.CompleteChatAsync(
    [new UserChatMessage("How can I solve 8x + 7 = -23?")],
    options);

using JsonDocument json = JsonDocument.Parse(completion.Content[0].Text);
Console.WriteLine($"Answer: {json.RootElement.GetProperty("final_answer")}");

Reasoning Models (o1, o4-mini)

推理模型(o1, o4-mini)

csharp
ChatCompletionOptions options = new()
{
    ReasoningEffortLevel = ChatReasoningEffortLevel.Low,
    MaxOutputTokenCount = 100000
};

ChatCompletion completion = await chatClient.CompleteChatAsync(
[
    new DeveloperChatMessage("You are a helpful assistant"),
    new UserChatMessage("Explain the theory of relativity")
], options);
csharp
ChatCompletionOptions options = new()
{
    ReasoningEffortLevel = ChatReasoningEffortLevel.Low,
    MaxOutputTokenCount = 100000
};

ChatCompletion completion = await chatClient.CompleteChatAsync(
[
    new DeveloperChatMessage("You are a helpful assistant"),
    new UserChatMessage("Explain the theory of relativity")
], options);

Azure AI Search Integration (RAG)

Azure AI Search集成(RAG)

csharp
using Azure.AI.OpenAI.Chat;

#pragma warning disable AOAI001

ChatCompletionOptions options = new();
options.AddDataSource(new AzureSearchChatDataSource()
{
    Endpoint = new Uri(searchEndpoint),
    IndexName = searchIndex,
    Authentication = DataSourceAuthentication.FromApiKey(searchKey)
});

ChatCompletion completion = await chatClient.CompleteChatAsync(
    [new UserChatMessage("What health plans are available?")],
    options);

ChatMessageContext context = completion.GetMessageContext();
if (context?.Intent is not null)
{
    Console.WriteLine($"Intent: {context.Intent}");
}
foreach (ChatCitation citation in context?.Citations ?? [])
{
    Console.WriteLine($"Citation: {citation.Content}");
}
csharp
using Azure.AI.OpenAI.Chat;

#pragma warning disable AOAI001

ChatCompletionOptions options = new();
options.AddDataSource(new AzureSearchChatDataSource()
{
    Endpoint = new Uri(searchEndpoint),
    IndexName = searchIndex,
    Authentication = DataSourceAuthentication.FromApiKey(searchKey)
});

ChatCompletion completion = await chatClient.CompleteChatAsync(
    [new UserChatMessage("What health plans are available?")],
    options);

ChatMessageContext context = completion.GetMessageContext();
if (context?.Intent is not null)
{
    Console.WriteLine($"Intent: {context.Intent}");
}
foreach (ChatCitation citation in context?.Citations ?? [])
{
    Console.WriteLine($"Citation: {citation.Content}");
}

Embeddings

嵌入

csharp
using OpenAI.Embeddings;

EmbeddingClient embeddingClient = azureClient.GetEmbeddingClient("text-embedding-ada-002");

OpenAIEmbedding embedding = await embeddingClient.GenerateEmbeddingAsync("Hello, world!");
ReadOnlyMemory<float> vector = embedding.ToFloats();

Console.WriteLine($"Embedding dimensions: {vector.Length}");
csharp
using OpenAI.Embeddings;

EmbeddingClient embeddingClient = azureClient.GetEmbeddingClient("text-embedding-ada-002");

OpenAIEmbedding embedding = await embeddingClient.GenerateEmbeddingAsync("Hello, world!");
ReadOnlyMemory<float> vector = embedding.ToFloats();

Console.WriteLine($"Embedding dimensions: {vector.Length}");

Batch Embeddings

批量嵌入

csharp
List<string> inputs = new()
{
    "First document text",
    "Second document text",
    "Third document text"
};

OpenAIEmbeddingCollection embeddings = await embeddingClient.GenerateEmbeddingsAsync(inputs);

foreach (OpenAIEmbedding emb in embeddings)
{
    Console.WriteLine($"Index {emb.Index}: {emb.ToFloats().Length} dimensions");
}
csharp
List<string> inputs = new()
{
    "First document text",
    "Second document text",
    "Third document text"
};

OpenAIEmbeddingCollection embeddings = await embeddingClient.GenerateEmbeddingsAsync(inputs);

foreach (OpenAIEmbedding emb in embeddings)
{
    Console.WriteLine($"Index {emb.Index}: {emb.ToFloats().Length} dimensions");
}

Image Generation (DALL-E)

图像生成(DALL-E)

csharp
using OpenAI.Images;

ImageClient imageClient = azureClient.GetImageClient("dall-e-3");

GeneratedImage image = await imageClient.GenerateImageAsync(
    "A futuristic city skyline at sunset",
    new ImageGenerationOptions
    {
        Size = GeneratedImageSize.W1024xH1024,
        Quality = GeneratedImageQuality.High,
        Style = GeneratedImageStyle.Vivid
    });

Console.WriteLine($"Image URL: {image.ImageUri}");
csharp
using OpenAI.Images;

ImageClient imageClient = azureClient.GetImageClient("dall-e-3");

GeneratedImage image = await imageClient.GenerateImageAsync(
    "A futuristic city skyline at sunset",
    new ImageGenerationOptions
    {
        Size = GeneratedImageSize.W1024xH1024,
        Quality = GeneratedImageQuality.High,
        Style = GeneratedImageStyle.Vivid
    });

Console.WriteLine($"Image URL: {image.ImageUri}");

Audio (Whisper)

音频(Whisper)

Transcription

转录

csharp
using OpenAI.Audio;

AudioClient audioClient = azureClient.GetAudioClient("whisper");

AudioTranscription transcription = await audioClient.TranscribeAudioAsync(
    "audio.mp3",
    new AudioTranscriptionOptions
    {
        ResponseFormat = AudioTranscriptionFormat.Verbose,
        Language = "en"
    });

Console.WriteLine(transcription.Text);
csharp
using OpenAI.Audio;

AudioClient audioClient = azureClient.GetAudioClient("whisper");

AudioTranscription transcription = await audioClient.TranscribeAudioAsync(
    "audio.mp3",
    new AudioTranscriptionOptions
    {
        ResponseFormat = AudioTranscriptionFormat.Verbose,
        Language = "en"
    });

Console.WriteLine(transcription.Text);

Text-to-Speech

文本转语音

csharp
BinaryData speech = await audioClient.GenerateSpeechAsync(
    "Hello, welcome to Azure OpenAI!",
    GeneratedSpeechVoice.Alloy,
    new SpeechGenerationOptions
    {
        SpeedRatio = 1.0f,
        ResponseFormat = GeneratedSpeechFormat.Mp3
    });

await File.WriteAllBytesAsync("output.mp3", speech.ToArray());
csharp
BinaryData speech = await audioClient.GenerateSpeechAsync(
    "Hello, welcome to Azure OpenAI!",
    GeneratedSpeechVoice.Alloy,
    new SpeechGenerationOptions
    {
        SpeedRatio = 1.0f,
        ResponseFormat = GeneratedSpeechFormat.Mp3
    });

await File.WriteAllBytesAsync("output.mp3", speech.ToArray());

Function Calling (Tools)

函数调用(工具)

csharp
ChatTool getCurrentWeatherTool = ChatTool.CreateFunctionTool(
    functionName: "get_current_weather",
    functionDescription: "Get the current weather in a given location",
    functionParameters: BinaryData.FromString("""
        {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA"
                },
                "unit": {
                    "type": "string",
                    "enum": ["celsius", "fahrenheit"]
                }
            },
            "required": ["location"]
        }
        """));

ChatCompletionOptions options = new()
{
    Tools = { getCurrentWeatherTool }
};

ChatCompletion completion = await chatClient.CompleteChatAsync(
    [new UserChatMessage("What's the weather in Seattle?")],
    options);

if (completion.FinishReason == ChatFinishReason.ToolCalls)
{
    foreach (ChatToolCall toolCall in completion.ToolCalls)
    {
        Console.WriteLine($"Function: {toolCall.FunctionName}");
        Console.WriteLine($"Arguments: {toolCall.FunctionArguments}");
    }
}
csharp
ChatTool getCurrentWeatherTool = ChatTool.CreateFunctionTool(
    functionName: "get_current_weather",
    functionDescription: "Get the current weather in a given location",
    functionParameters: BinaryData.FromString("""
        {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA"
                },
                "unit": {
                    "type": "string",
                    "enum": ["celsius", "fahrenheit"]
                }
            },
            "required": ["location"]
        }
        """));

ChatCompletionOptions options = new()
{
    Tools = { getCurrentWeatherTool }
};

ChatCompletion completion = await chatClient.CompleteChatAsync(
    [new UserChatMessage("What's the weather in Seattle?")],
    options);

if (completion.FinishReason == ChatFinishReason.ToolCalls)
{
    foreach (ChatToolCall toolCall in completion.ToolCalls)
    {
        Console.WriteLine($"Function: {toolCall.FunctionName}");
        Console.WriteLine($"Arguments: {toolCall.FunctionArguments}");
    }
}

Key Types Reference

关键类型参考

TypePurpose
AzureOpenAIClient
Top-level client for Azure OpenAI
ChatClient
Chat completions
EmbeddingClient
Text embeddings
ImageClient
Image generation (DALL-E)
AudioClient
Audio transcription/TTS
ChatCompletion
Chat response
ChatCompletionOptions
Request configuration
StreamingChatCompletionUpdate
Streaming response chunk
ChatMessage
Base message type
SystemChatMessage
System prompt
UserChatMessage
User input
AssistantChatMessage
Assistant response
DeveloperChatMessage
Developer message (reasoning models)
ChatTool
Function/tool definition
ChatToolCall
Tool invocation request
类型用途
AzureOpenAIClient
Azure OpenAI的顶级客户端
ChatClient
聊天补全
EmbeddingClient
文本嵌入
ImageClient
图像生成(DALL-E)
AudioClient
音频转录/文本转语音
ChatCompletion
聊天响应
ChatCompletionOptions
请求配置
StreamingChatCompletionUpdate
流式响应块
ChatMessage
基础消息类型
SystemChatMessage
系统提示词
UserChatMessage
用户输入
AssistantChatMessage
助手响应
DeveloperChatMessage
开发者消息(推理模型)
ChatTool
函数/工具定义
ChatToolCall
工具调用请求

Best Practices

最佳实践

  1. Use Entra ID in production — Avoid API keys; use
    DefaultAzureCredential
  2. Reuse client instances — Create once, share across requests
  3. Handle rate limits — Implement exponential backoff for 429 errors
  4. Stream for long responses — Use
    CompleteChatStreamingAsync
    for better UX
  5. Set appropriate timeouts — Long completions may need extended timeouts
  6. Use structured outputs — JSON schema ensures consistent response format
  7. Monitor token usage — Track
    completion.Usage
    for cost management
  8. Validate tool calls — Always validate function arguments before execution
  1. 生产环境使用Entra ID — 避免使用API密钥;使用
    DefaultAzureCredential
  2. 复用客户端实例 — 仅创建一次,在多个请求中共享
  3. 处理速率限制 — 针对429错误实现指数退避策略
  4. 长响应使用流式传输 — 使用
    CompleteChatStreamingAsync
    提升用户体验
  5. 设置合适的超时时间 — 长文本补全可能需要延长超时时间
  6. 使用结构化输出 — JSON Schema确保响应格式一致
  7. 监控令牌使用量 — 跟踪
    completion.Usage
    以管理成本
  8. 验证工具调用 — 执行前始终验证函数参数

Error Handling

错误处理

csharp
using Azure;

try
{
    ChatCompletion completion = await chatClient.CompleteChatAsync(messages);
}
catch (RequestFailedException ex) when (ex.Status == 429)
{
    Console.WriteLine("Rate limited. Retry after delay.");
    await Task.Delay(TimeSpan.FromSeconds(10));
}
catch (RequestFailedException ex) when (ex.Status == 400)
{
    Console.WriteLine($"Bad request: {ex.Message}");
}
catch (RequestFailedException ex)
{
    Console.WriteLine($"Azure OpenAI error: {ex.Status} - {ex.Message}");
}
csharp
using Azure;

try
{
    ChatCompletion completion = await chatClient.CompleteChatAsync(messages);
}
catch (RequestFailedException ex) when (ex.Status == 429)
{
    Console.WriteLine("Rate limited. Retry after delay.");
    await Task.Delay(TimeSpan.FromSeconds(10));
}
catch (RequestFailedException ex) when (ex.Status == 400)
{
    Console.WriteLine($"Bad request: {ex.Message}");
}
catch (RequestFailedException ex)
{
    Console.WriteLine($"Azure OpenAI error: {ex.Status} - {ex.Message}");
}

Related SDKs

相关SDK

SDKPurposeInstall
Azure.AI.OpenAI
Azure OpenAI client (this SDK)
dotnet add package Azure.AI.OpenAI
OpenAI
OpenAI compatibility
dotnet add package OpenAI
Azure.Identity
Authentication
dotnet add package Azure.Identity
Azure.Search.Documents
AI Search for RAG
dotnet add package Azure.Search.Documents
SDK用途安装命令
Azure.AI.OpenAI
Azure OpenAI客户端(本SDK)
dotnet add package Azure.AI.OpenAI
OpenAI
兼容OpenAI
dotnet add package OpenAI
Azure.Identity
认证
dotnet add package Azure.Identity
Azure.Search.Documents
用于RAG的AI搜索
dotnet add package Azure.Search.Documents

Reference Links

参考链接