[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73EK2RG58HCMSAE6NEGP7AM":3,"skill-same:01M73EK2RG58HCMSAE6NEGP7AM":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M73EK2RG58HCMSAE6NEGP7AM","azure-ai-openai-dotnet",null,"Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants. Triggers: \"Azure OpenAI\", \"AzureOpenAIClient\", \"ChatClient\", \"chat completions .NET\", \"GPT-4\", \"embeddings\", \"DALL-E\", \"Whisper\", \"OpenAI .NET\".","qhjqhj00\u002Fresearch-skills-pool","qhjqhj00","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F29684092?v=4","01M72AE0ZGXVM5C57N512DGQG8","Tommy Chien","01M72AE107ESJMHT7QC5SXX144",3,"MIT","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-sdk-dotnet__skills__azure-ai-openai-dotnet\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: azure-ai-openai-dotnet\ndescription: |\n  Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants. Triggers: \"Azure OpenAI\", \"AzureOpenAIClient\", \"ChatClient\", \"chat completions .NET\", \"GPT-4\", \"embeddings\", \"DALL-E\", \"Whisper\", \"OpenAI .NET\".\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: Azure.AI.OpenAI\n---\n\n# Azure.AI.OpenAI (.NET)\n\nClient library for Azure OpenAI Service providing access to OpenAI models including GPT-4, GPT-4o, embeddings, DALL-E, and Whisper.\n\n## Installation\n\n```bash\ndotnet add package Azure.AI.OpenAI\n\n# For OpenAI (non-Azure) compatibility\ndotnet add package OpenAI\n```\n\n**Current Version**: 2.1.0 (stable)\n\n## Environment Variables\n\n```bash\nAZURE_OPENAI_ENDPOINT=https:\u002F\u002F\u003Cresource-name>.openai.azure.com  # Required: Azure OpenAI endpoint\nAZURE_OPENAI_API_KEY=\u003Capi-key>  # Only required for AzureKeyCredential auth\nAZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-mini  # Required: model deployment name\nAZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production\n```\n\n## Client Hierarchy\n\n```\nAzureOpenAIClient (top-level)\n├── GetChatClient(deploymentName)      → ChatClient\n├── GetEmbeddingClient(deploymentName) → EmbeddingClient\n├── GetImageClient(deploymentName)     → ImageClient\n├── GetAudioClient(deploymentName)     → AudioClient\n└── GetAssistantClient()               → AssistantClient\n```\n\n## Authentication\n\n### API Key Authentication\n\n```csharp\nusing Azure;\nusing Azure.AI.OpenAI;\n\nAzureOpenAIClient client = new(\n    new Uri(Environment.GetEnvironmentVariable(\"AZURE_OPENAI_ENDPOINT\")!),\n    new AzureKeyCredential(Environment.GetEnvironmentVariable(\"AZURE_OPENAI_API_KEY\")!));\n```\n\n### Microsoft Entra Token Credential\n\n```csharp\nusing Azure.Identity;\nusing Azure.AI.OpenAI;\n\n\u002F\u002F Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\nvar credential = new DefaultAzureCredential(\n    DefaultAzureCredential.DefaultEnvironmentVariableName\n);\n\u002F\u002F Or use a specific credential directly in production:\n\u002F\u002F See https:\u002F\u002Flearn.microsoft.com\u002Fdotnet\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-dotnet#credential-classes\n\u002F\u002F var credential = new ManagedIdentityCredential();\nAzureOpenAIClient client = new(\n    new Uri(Environment.GetEnvironmentVariable(\"AZURE_OPENAI_ENDPOINT\")!),\n    credential);\n```\n\n### Using OpenAI SDK Directly with Azure\n\n```csharp\nusing Azure.Identity;\nusing OpenAI;\nusing OpenAI.Chat;\nusing System.ClientModel.Primitives;\n\n#pragma warning disable OPENAI001\n\nBearerTokenPolicy tokenPolicy = new(\n    new DefaultAzureCredential(),\n    \"https:\u002F\u002Fcognitiveservices.azure.com\u002F.default\");\n\nChatClient client = new(\n    model: \"gpt-4o-mini\",\n    authenticationPolicy: tokenPolicy,\n    options: new OpenAIClientOptions()\n    {\n        Endpoint = new Uri(\"https:\u002F\u002FYOUR-RESOURCE.openai.azure.com\u002Fopenai\u002Fv1\")\n    });\n```\n\n## Chat Completions\n\n### Basic Chat\n\n```csharp\nusing Azure.AI.OpenAI;\nusing OpenAI.Chat;\n\nAzureOpenAIClient azureClient = new(\n    new Uri(endpoint),\n    new DefaultAzureCredential());\n\nChatClient chatClient = azureClient.GetChatClient(\"gpt-4o-mini\");\n\nChatCompletion completion = chatClient.CompleteChat(\n[\n    new SystemChatMessage(\"You are a helpful assistant.\"),\n    new UserChatMessage(\"What is Azure OpenAI?\")\n]);\n\nConsole.WriteLine(completion.Content[0].Text);\n```\n\n### Async Chat\n\n```csharp\nChatCompletion completion = await chatClient.CompleteChatAsync(\n[\n    new SystemChatMessage(\"You are a helpful assistant.\"),\n    new UserChatMessage(\"Explain cloud computing in simple terms.\")\n]);\n\nConsole.WriteLine($\"Response: {completion.Content[0].Text}\");\nConsole.WriteLine($\"Tokens used: {completion.Usage.TotalTokenCount}\");\n```\n\n### Streaming Chat\n\n```csharp\nawait foreach (StreamingChatCompletionUpdate update \n    in chatClient.CompleteChatStreamingAsync(messages))\n{\n    if (update.ContentUpdate.Count > 0)\n    {\n        Console.Write(update.ContentUpdate[0].Text);\n    }\n}\n```\n\n### Chat with Options\n\n```csharp\nChatCompletionOptions options = new()\n{\n    MaxOutputTokenCount = 1000,\n    Temperature = 0.7f,\n    TopP = 0.95f,\n    FrequencyPenalty = 0,\n    PresencePenalty = 0\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(messages, options);\n```\n\n### Multi-turn Conversation\n\n```csharp\nList\u003CChatMessage> messages = new()\n{\n    new SystemChatMessage(\"You are a helpful assistant.\"),\n    new UserChatMessage(\"Hi, can you help me?\"),\n    new AssistantChatMessage(\"Of course! What do you need help with?\"),\n    new UserChatMessage(\"What's the capital of France?\")\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(messages);\nmessages.Add(new AssistantChatMessage(completion.Content[0].Text));\n```\n\n## Structured Outputs (JSON Schema)\n\n```csharp\nusing System.Text.Json;\n\nChatCompletionOptions options = new()\n{\n    ResponseFormat = ChatResponseFormat.CreateJsonSchemaFormat(\n        jsonSchemaFormatName: \"math_reasoning\",\n        jsonSchema: BinaryData.FromBytes(\"\"\"\n            {\n                \"type\": \"object\",\n                \"properties\": {\n                    \"steps\": {\n                        \"type\": \"array\",\n                        \"items\": {\n                            \"type\": \"object\",\n                            \"properties\": {\n                                \"explanation\": { \"type\": \"string\" },\n                                \"output\": { \"type\": \"string\" }\n                            },\n                            \"required\": [\"explanation\", \"output\"],\n                            \"additionalProperties\": false\n                        }\n                    },\n                    \"final_answer\": { \"type\": \"string\" }\n                },\n                \"required\": [\"steps\", \"final_answer\"],\n                \"additionalProperties\": false\n            }\n            \"\"\"u8.ToArray()),\n        jsonSchemaIsStrict: true)\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(\n    [new UserChatMessage(\"How can I solve 8x + 7 = -23?\")],\n    options);\n\nusing JsonDocument json = JsonDocument.Parse(completion.Content[0].Text);\nConsole.WriteLine($\"Answer: {json.RootElement.GetProperty(\"final_answer\")}\");\n```\n\n## Reasoning Models (o1, o4-mini)\n\n```csharp\nChatCompletionOptions options = new()\n{\n    ReasoningEffortLevel = ChatReasoningEffortLevel.Low,\n    MaxOutputTokenCount = 100000\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(\n[\n    new DeveloperChatMessage(\"You are a helpful assistant\"),\n    new UserChatMessage(\"Explain the theory of relativity\")\n], options);\n```\n\n## Azure AI Search Integration (RAG)\n\n```csharp\nusing Azure.AI.OpenAI.Chat;\n\n#pragma warning disable AOAI001\n\nChatCompletionOptions options = new();\noptions.AddDataSource(new AzureSearchChatDataSource()\n{\n    Endpoint = new Uri(searchEndpoint),\n    IndexName = searchIndex,\n    Authentication = DataSourceAuthentication.FromApiKey(searchKey)\n});\n\nChatCompletion completion = await chatClient.CompleteChatAsync(\n    [new UserChatMessage(\"What health plans are available?\")],\n    options);\n\nChatMessageContext context = completion.GetMessageContext();\nif (context?.Intent is not null)\n{\n    Console.WriteLine($\"Intent: {context.Intent}\");\n}\nforeach (ChatCitation citation in context?.Citations ?? [])\n{\n    Console.WriteLine($\"Citation: {citation.Content}\");\n}\n```\n\n## Embeddings\n\n```csharp\nusing OpenAI.Embeddings;\n\nEmbeddingClient embeddingClient = azureClient.GetEmbeddingClient(\"text-embedding-ada-002\");\n\nOpenAIEmbedding embedding = await embeddingClient.GenerateEmbeddingAsync(\"Hello, world!\");\nReadOnlyMemory\u003Cfloat> vector = embedding.ToFloats();\n\nConsole.WriteLine($\"Embedding dimensions: {vector.Length}\");\n```\n\n### Batch Embeddings\n\n```csharp\nList\u003Cstring> inputs = new()\n{\n    \"First document text\",\n    \"Second document text\",\n    \"Third document text\"\n};\n\nOpenAIEmbeddingCollection embeddings = await embeddingClient.GenerateEmbeddingsAsync(inputs);\n\nforeach (OpenAIEmbedding emb in embeddings)\n{\n    Console.WriteLine($\"Index {emb.Index}: {emb.ToFloats().Length} dimensions\");\n}\n```\n\n## Image Generation (DALL-E)\n\n```csharp\nusing OpenAI.Images;\n\nImageClient imageClient = azureClient.GetImageClient(\"dall-e-3\");\n\nGeneratedImage image = await imageClient.GenerateImageAsync(\n    \"A futuristic city skyline at sunset\",\n    new ImageGenerationOptions\n    {\n        Size = GeneratedImageSize.W1024xH1024,\n        Quality = GeneratedImageQuality.High,\n        Style = GeneratedImageStyle.Vivid\n    });\n\nConsole.WriteLine($\"Image URL: {image.ImageUri}\");\n```\n\n## Audio (Whisper)\n\n### Transcription\n\n```csharp\nusing OpenAI.Audio;\n\nAudioClient audioClient = azureClient.GetAudioClient(\"whisper\");\n\nAudioTranscription transcription = await audioClient.TranscribeAudioAsync(\n    \"audio.mp3\",\n    new AudioTranscriptionOptions\n    {\n        ResponseFormat = AudioTranscriptionFormat.Verbose,\n        Language = \"en\"\n    });\n\nConsole.WriteLine(transcription.Text);\n```\n\n### Text-to-Speech\n\n```csharp\nBinaryData speech = await audioClient.GenerateSpeechAsync(\n    \"Hello, welcome to Azure OpenAI!\",\n    GeneratedSpeechVoice.Alloy,\n    new SpeechGenerationOptions\n    {\n        SpeedRatio = 1.0f,\n        ResponseFormat = GeneratedSpeechFormat.Mp3\n    });\n\nawait File.WriteAllBytesAsync(\"output.mp3\", speech.ToArray());\n```\n\n## Function Calling (Tools)\n\n```csharp\nChatTool getCurrentWeatherTool = ChatTool.CreateFunctionTool(\n    functionName: \"get_current_weather\",\n    functionDescription: \"Get the current weather in a given location\",\n    functionParameters: BinaryData.FromString(\"\"\"\n        {\n            \"type\": \"object\",\n            \"properties\": {\n                \"location\": {\n                    \"type\": \"string\",\n                    \"description\": \"The city and state, e.g. San Francisco, CA\"\n                },\n                \"unit\": {\n                    \"type\": \"string\",\n                    \"enum\": [\"celsius\", \"fahrenheit\"]\n                }\n            },\n            \"required\": [\"location\"]\n        }\n        \"\"\"));\n\nChatCompletionOptions options = new()\n{\n    Tools = { getCurrentWeatherTool }\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(\n    [new UserChatMessage(\"What's the weather in Seattle?\")],\n    options);\n\nif (completion.FinishReason == ChatFinishReason.ToolCalls)\n{\n    foreach (ChatToolCall toolCall in completion.ToolCalls)\n    {\n        Console.WriteLine($\"Function: {toolCall.FunctionName}\");\n        Console.WriteLine($\"Arguments: {toolCall.FunctionArguments}\");\n    }\n}\n```\n\n## Key Types Reference\n\n| Type | Purpose |\n|------|---------|\n| `AzureOpenAIClient` | Top-level client for Azure OpenAI |\n| `ChatClient` | Chat completions |\n| `EmbeddingClient` | Text embeddings |\n| `ImageClient` | Image generation (DALL-E) |\n| `AudioClient` | Audio transcription\u002FTTS |\n| `ChatCompletion` | Chat response |\n| `ChatCompletionOptions` | Request configuration |\n| `StreamingChatCompletionUpdate` | Streaming response chunk |\n| `ChatMessage` | Base message type |\n| `SystemChatMessage` | System prompt |\n| `UserChatMessage` | User input |\n| `AssistantChatMessage` | Assistant response |\n| `DeveloperChatMessage` | Developer message (reasoning models) |\n| `ChatTool` | Function\u002Ftool definition |\n| `ChatToolCall` | Tool invocation request |\n\n## Best Practices\n\n1. **Use Entra ID in production** — Avoid API keys; use `DefaultAzureCredential`\n2. **Reuse client instances** — Create once, share across requests\n3. **Handle rate limits** — Implement exponential backoff for 429 errors\n4. **Stream for long responses** — Use `CompleteChatStreamingAsync` for better UX\n5. **Set appropriate timeouts** — Long completions may need extended timeouts\n6. **Use structured outputs** — JSON schema ensures consistent response format\n7. **Monitor token usage** — Track `completion.Usage` for cost management\n8. **Validate tool calls** — Always validate function arguments before execution\n\n## Error Handling\n\n```csharp\nusing Azure;\n\ntry\n{\n    ChatCompletion completion = await chatClient.CompleteChatAsync(messages);\n}\ncatch (RequestFailedException ex) when (ex.Status == 429)\n{\n    Console.WriteLine(\"Rate limited. Retry after delay.\");\n    await Task.Delay(TimeSpan.FromSeconds(10));\n}\ncatch (RequestFailedException ex) when (ex.Status == 400)\n{\n    Console.WriteLine($\"Bad request: {ex.Message}\");\n}\ncatch (RequestFailedException ex)\n{\n    Console.WriteLine($\"Azure OpenAI error: {ex.Status} - {ex.Message}\");\n}\n```\n\n## Related SDKs\n\n| SDK | Purpose | Install |\n|-----|---------|---------|\n| `Azure.AI.OpenAI` | Azure OpenAI client (this SDK) | `dotnet add package Azure.AI.OpenAI` |\n| `OpenAI` | OpenAI compatibility | `dotnet add package OpenAI` |\n| `Azure.Identity` | Authentication | `dotnet add package Azure.Identity` |\n| `Azure.Search.Documents` | AI Search for RAG | `dotnet add package Azure.Search.Documents` |\n\n## Reference Links\n\n| Resource | URL |\n|----------|-----|\n| NuGet Package | https:\u002F\u002Fwww.nuget.org\u002Fpackages\u002FAzure.AI.OpenAI |\n| API Reference | https:\u002F\u002Flearn.microsoft.com\u002Fdotnet\u002Fapi\u002Fazure.ai.openai |\n| Migration Guide (1.0→2.0) | https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fopenai\u002Fhow-to\u002Fdotnet-migration |\n| Quickstart | https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fopenai\u002Fquickstart |\n| GitHub Source | https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-sdk-for-net\u002Ftree\u002Fmain\u002Fsdk\u002Fopenai\u002FAzure.AI.OpenAI |\n","# Azure.AI.OpenAI (.NET)\n\nClient library for Azure OpenAI Service providing access to OpenAI models including GPT-4, GPT-4o, embeddings, DALL-E, and Whisper.\n\n## Installation\n\n```bash\ndotnet add package Azure.AI.OpenAI\n\n# For OpenAI (non-Azure) compatibility\ndotnet add package OpenAI\n```\n\n**Current Version**: 2.1.0 (stable)\n\n## Environment Variables\n\n```bash\nAZURE_OPENAI_ENDPOINT=https:\u002F\u002F\u003Cresource-name>.openai.azure.com  # Required: Azure OpenAI endpoint\nAZURE_OPENAI_API_KEY=\u003Capi-key>  # Only required for AzureKeyCredential auth\nAZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-mini  # Required: model deployment name\nAZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production\n```\n\n## Client Hierarchy\n\n```\nAzureOpenAIClient (top-level)\n├── GetChatClient(deploymentName)      → ChatClient\n├── GetEmbeddingClient(deploymentName) → EmbeddingClient\n├── GetImageClient(deploymentName)     → ImageClient\n├── GetAudioClient(deploymentName)     → AudioClient\n└── GetAssistantClient()               → AssistantClient\n```\n\n## Authentication\n\n### API Key Authentication\n\n```csharp\nusing Azure;\nusing Azure.AI.OpenAI;\n\nAzureOpenAIClient client = new(\n    new Uri(Environment.GetEnvironmentVariable(\"AZURE_OPENAI_ENDPOINT\")!),\n    new AzureKeyCredential(Environment.GetEnvironmentVariable(\"AZURE_OPENAI_API_KEY\")!));\n```\n\n### Microsoft Entra Token Credential\n\n```csharp\nusing Azure.Identity;\nusing Azure.AI.OpenAI;\n\n\u002F\u002F Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\nvar credential = new DefaultAzureCredential(\n    DefaultAzureCredential.DefaultEnvironmentVariableName\n);\n\u002F\u002F Or use a specific credential directly in production:\n\u002F\u002F See https:\u002F\u002Flearn.microsoft.com\u002Fdotnet\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-dotnet#credential-classes\n\u002F\u002F var credential = new ManagedIdentityCredential();\nAzureOpenAIClient client = new(\n    new Uri(Environment.GetEnvironmentVariable(\"AZURE_OPENAI_ENDPOINT\")!),\n    credential);\n```\n\n### Using OpenAI SDK Directly with Azure\n\n```csharp\nusing Azure.Identity;\nusing OpenAI;\nusing OpenAI.Chat;\nusing System.ClientModel.Primitives;\n\n#pragma warning disable OPENAI001\n\nBearerTokenPolicy tokenPolicy = new(\n    new DefaultAzureCredential(),\n    \"https:\u002F\u002Fcognitiveservices.azure.com\u002F.default\");\n\nChatClient client = new(\n    model: \"gpt-4o-mini\",\n    authenticationPolicy: tokenPolicy,\n    options: new OpenAIClientOptions()\n    {\n        Endpoint = new Uri(\"https:\u002F\u002FYOUR-RESOURCE.openai.azure.com\u002Fopenai\u002Fv1\")\n    });\n```\n\n## Chat Completions\n\n### Basic Chat\n\n```csharp\nusing Azure.AI.OpenAI;\nusing OpenAI.Chat;\n\nAzureOpenAIClient azureClient = new(\n    new Uri(endpoint),\n    new DefaultAzureCredential());\n\nChatClient chatClient = azureClient.GetChatClient(\"gpt-4o-mini\");\n\nChatCompletion completion = chatClient.CompleteChat(\n[\n    new SystemChatMessage(\"You are a helpful assistant.\"),\n    new UserChatMessage(\"What is Azure OpenAI?\")\n]);\n\nConsole.WriteLine(completion.Content[0].Text);\n```\n\n### Async Chat\n\n```csharp\nChatCompletion completion = await chatClient.CompleteChatAsync(\n[\n    new SystemChatMessage(\"You are a helpful assistant.\"),\n    new UserChatMessage(\"Explain cloud computing in simple terms.\")\n]);\n\nConsole.WriteLine($\"Response: {completion.Content[0].Text}\");\nConsole.WriteLine($\"Tokens used: {completion.Usage.TotalTokenCount}\");\n```\n\n### Streaming Chat\n\n```csharp\nawait foreach (StreamingChatCompletionUpdate update \n    in chatClient.CompleteChatStreamingAsync(messages))\n{\n    if (update.ContentUpdate.Count > 0)\n    {\n        Console.Write(update.ContentUpdate[0].Text);\n    }\n}\n```\n\n### Chat with Options\n\n```csharp\nChatCompletionOptions options = new()\n{\n    MaxOutputTokenCount = 1000,\n    Temperature = 0.7f,\n    TopP = 0.95f,\n    FrequencyPenalty = 0,\n    PresencePenalty = 0\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(messages, options);\n```\n\n### Multi-turn Conversation\n\n```csharp\nList\u003CChatMessage> messages = new()\n{\n    new SystemChatMessage(\"You are a helpful assistant.\"),\n    new UserChatMessage(\"Hi, can you help me?\"),\n    new AssistantChatMessage(\"Of course! What do you need help with?\"),\n    new UserChatMessage(\"What's the capital of France?\")\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(messages);\nmessages.Add(new AssistantChatMessage(completion.Content[0].Text));\n```\n\n## Structured Outputs (JSON Schema)\n\n```csharp\nusing System.Text.Json;\n\nChatCompletionOptions options = new()\n{\n    ResponseFormat = ChatResponseFormat.CreateJsonSchemaFormat(\n        jsonSchemaFormatName: \"math_reasoning\",\n        jsonSchema: BinaryData.FromBytes(\"\"\"\n            {\n                \"type\": \"object\",\n                \"properties\": {\n                    \"steps\": {\n                        \"type\": \"array\",\n                        \"items\": {\n                            \"type\": \"object\",\n                            \"properties\": {\n                                \"explanation\": { \"type\": \"string\" },\n                                \"output\": { \"type\": \"string\" }\n                            },\n                            \"required\": [\"explanation\", \"output\"],\n                            \"additionalProperties\": false\n                        }\n                    },\n                    \"final_answer\": { \"type\": \"string\" }\n                },\n                \"required\": [\"steps\", \"final_answer\"],\n                \"additionalProperties\": false\n            }\n            \"\"\"u8.ToArray()),\n        jsonSchemaIsStrict: true)\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(\n    [new UserChatMessage(\"How can I solve 8x + 7 = -23?\")],\n    options);\n\nusing JsonDocument json = JsonDocument.Parse(completion.Content[0].Text);\nConsole.WriteLine($\"Answer: {json.RootElement.GetProperty(\"final_answer\")}\");\n```\n\n## Reasoning Models (o1, o4-mini)\n\n```csharp\nChatCompletionOptions options = new()\n{\n    ReasoningEffortLevel = ChatReasoningEffortLevel.Low,\n    MaxOutputTokenCount = 100000\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(\n[\n    new DeveloperChatMessage(\"You are a helpful assistant\"),\n    new UserChatMessage(\"Explain the theory of relativity\")\n], options);\n```\n\n## Azure AI Search Integration (RAG)\n\n```csharp\nusing Azure.AI.OpenAI.Chat;\n\n#pragma warning disable AOAI001\n\nChatCompletionOptions options = new();\noptions.AddDataSource(new AzureSearchChatDataSource()\n{\n    Endpoint = new Uri(searchEndpoint),\n    IndexName = searchIndex,\n    Authentication = DataSourceAuthentication.FromApiKey(searchKey)\n});\n\nChatCompletion completion = await chatClient.CompleteChatAsync(\n    [new UserChatMessage(\"What health plans are available?\")],\n    options);\n\nChatMessageContext context = completion.GetMessageContext();\nif (context?.Intent is not null)\n{\n    Console.WriteLine($\"Intent: {context.Intent}\");\n}\nforeach (ChatCitation citation in context?.Citations ?? [])\n{\n    Console.WriteLine($\"Citation: {citation.Content}\");\n}\n```\n\n## Embeddings\n\n```csharp\nusing OpenAI.Embeddings;\n\nEmbeddingClient embeddingClient = azureClient.GetEmbeddingClient(\"text-embedding-ada-002\");\n\nOpenAIEmbedding embedding = await embeddingClient.GenerateEmbeddingAsync(\"Hello, world!\");\nReadOnlyMemory\u003Cfloat> vector = embedding.ToFloats();\n\nConsole.WriteLine($\"Embedding dimensions: {vector.Length}\");\n```\n\n### Batch Embeddings\n\n```csharp\nList\u003Cstring> inputs = new()\n{\n    \"First document text\",\n    \"Second document text\",\n    \"Third document text\"\n};\n\nOpenAIEmbeddingCollection embeddings = await embeddingClient.GenerateEmbeddingsAsync(inputs);\n\nforeach (OpenAIEmbedding emb in embeddings)\n{\n    Console.WriteLine($\"Index {emb.Index}: {emb.ToFloats().Length} dimensions\");\n}\n```\n\n## Image Generation (DALL-E)\n\n```csharp\nusing OpenAI.Images;\n\nImageClient imageClient = azureClient.GetImageClient(\"dall-e-3\");\n\nGeneratedImage image = await imageClient.GenerateImageAsync(\n    \"A futuristic city skyline at sunset\",\n    new ImageGenerationOptions\n    {\n        Size = GeneratedImageSize.W1024xH1024,\n        Quality = GeneratedImageQuality.High,\n        Style = GeneratedImageStyle.Vivid\n    });\n\nConsole.WriteLine($\"Image URL: {image.ImageUri}\");\n```\n\n## Audio (Whisper)\n\n### Transcription\n\n```csharp\nusing OpenAI.Audio;\n\nAudioClient audioClient = azureClient.GetAudioClient(\"whisper\");\n\nAudioTranscription transcription = await audioClient.TranscribeAudioAsync(\n    \"audio.mp3\",\n    new AudioTranscriptionOptions\n    {\n        ResponseFormat = AudioTranscriptionFormat.Verbose,\n        Language = \"en\"\n    });\n\nConsole.WriteLine(transcription.Text);\n```\n\n### Text-to-Speech\n\n```csharp\nBinaryData speech = await audioClient.GenerateSpeechAsync(\n    \"Hello, welcome to Azure OpenAI!\",\n    GeneratedSpeechVoice.Alloy,\n    new SpeechGenerationOptions\n    {\n        SpeedRatio = 1.0f,\n        ResponseFormat = GeneratedSpeechFormat.Mp3\n    });\n\nawait File.WriteAllBytesAsync(\"output.mp3\", speech.ToArray());\n```\n\n## Function Calling (Tools)\n\n```csharp\nChatTool getCurrentWeatherTool = ChatTool.CreateFunctionTool(\n    functionName: \"get_current_weather\",\n    functionDescription: \"Get the current weather in a given location\",\n    functionParameters: BinaryData.FromString(\"\"\"\n        {\n            \"type\": \"object\",\n            \"properties\": {\n                \"location\": {\n                    \"type\": \"string\",\n                    \"description\": \"The city and state, e.g. San Francisco, CA\"\n                },\n                \"unit\": {\n                    \"type\": \"string\",\n                    \"enum\": [\"celsius\", \"fahrenheit\"]\n                }\n            },\n            \"required\": [\"location\"]\n        }\n        \"\"\"));\n\nChatCompletionOptions options = new()\n{\n    Tools = { getCurrentWeatherTool }\n};\n\nChatCompletion completion = await chatClient.CompleteChatAsync(\n    [new UserChatMessage(\"What's the weather in Seattle?\")],\n    options);\n\nif (completion.FinishReason == ChatFinishReason.ToolCalls)\n{\n    foreach (ChatToolCall toolCall in completion.ToolCalls)\n    {\n        Console.WriteLine($\"Function: {toolCall.FunctionName}\");\n        Console.WriteLine($\"Arguments: {toolCall.FunctionArguments}\");\n    }\n}\n```\n\n## Key Types Reference\n\n| Type | Purpose |\n|------|---------|\n| `AzureOpenAIClient` | Top-level client for Azure OpenAI |\n| `ChatClient` | Chat completions |\n| `EmbeddingClient` | Text embeddings |\n| `ImageClient` | Image generation (DALL-E) |\n| `AudioClient` | Audio transcription\u002FTTS |\n| `ChatCompletion` | Chat response |\n| `ChatCompletionOptions` | Request configuration |\n| `StreamingChatCompletionUpdate` | Streaming response chunk |\n| `ChatMessage` | Base message type |\n| `SystemChatMessage` | System prompt |\n| `UserChatMessage` | User input |\n| `AssistantChatMessage` | Assistant response |\n| `DeveloperChatMessage` | Developer message (reasoning models) |\n| `ChatTool` | Function\u002Ftool definition |\n| `ChatToolCall` | Tool invocation request |\n\n## Best Practices\n\n1. **Use Entra ID in production** — Avoid API keys; use `DefaultAzureCredential`\n2. **Reuse client instances** — Create once, share across requests\n3. **Handle rate limits** — Implement exponential backoff for 429 errors\n4. **Stream for long responses** — Use `CompleteChatStreamingAsync` for better UX\n5. **Set appropriate timeouts** — Long completions may need extended timeouts\n6. **Use structured outputs** — JSON schema ensures consistent response format\n7. **Monitor token usage** — Track `completion.Usage` for cost management\n8. **Validate tool calls** — Always validate function arguments before execution\n\n## Error Handling\n\n```csharp\nusing Azure;\n\ntry\n{\n    ChatCompletion completion = await chatClient.CompleteChatAsync(messages);\n}\ncatch (RequestFailedException ex) when (ex.Status == 429)\n{\n    Console.WriteLine(\"Rate limited. Retry after delay.\");\n    await Task.Delay(TimeSpan.FromSeconds(10));\n}\ncatch (RequestFailedException ex) when (ex.Status == 400)\n{\n    Console.WriteLine($\"Bad request: {ex.Message}\");\n}\ncatch (RequestFailedException ex)\n{\n    Console.WriteLine($\"Azure OpenAI error: {ex.Status} - {ex.Message}\");\n}\n```\n\n## Related SDKs\n\n| SDK | Purpose | Install |\n|-----|---------|---------|\n| `Azure.AI.OpenAI` | Azure OpenAI client (this SDK) | `dotnet add package Azure.AI.OpenAI` |\n| `OpenAI` | OpenAI compatibility | `dotnet add package OpenAI` |\n| `Azure.Identity` | Authentication | `dotnet add package Azure.Identity` |\n| `Azure.Search.Documents` | AI Search for RAG | `dotnet add package Azure.Search.Documents` |\n\n## Reference Links\n\n| Resource | URL |\n|----------|-----|\n| NuGet Package | https:\u002F\u002Fwww.nuget.org\u002Fpackages\u002FAzure.AI.OpenAI |\n| API Reference | https:\u002F\u002Flearn.microsoft.com\u002Fdotnet\u002Fapi\u002Fazure.ai.openai |\n| Migration Guide (1.0→2.0) | https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fopenai\u002Fhow-to\u002Fdotnet-migration |\n| Quickstart | https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fopenai\u002Fquickstart |\n| GitHub Source | https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-sdk-for-net\u002Ftree\u002Fmain\u002Fsdk\u002Fopenai\u002FAzure.AI.OpenAI |\n",{"name":5,"license":15,"metadata":24,"description":28},{"author":25,"package":26,"version":27},"Microsoft","Azure.AI.OpenAI","1.0.0","Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants. Triggers: \"Azure OpenAI\", \"AzureOpenAIClient\", \"ChatClient\", \"chat completions .NET\", \"GPT-4\", \"embeddings\", \"DALL-E\", \"Whisper\", \"OpenAI .NET\".\n","master","c247302c836de6438d746b45670990eb71691166","skills_collected\u002Fmicrosoft--skills--.github__plugins__azure-sdk-dotnet__skills__azure-ai-openai-dotnet",1,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool","https:\u002F\u002Fgithub.com\u002Fqhjqhj00","chien.io","2026-05-11 15:07:59",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add qhjqhj00\u002Fresearch-skills-pool --skill azure-ai-openai-dotnet",{"tool":43,"command":44},"bunx","bunx skills add qhjqhj00\u002Fresearch-skills-pool --skill azure-ai-openai-dotnet",{"tool":46,"command":47},"pnpm","pnpm dlx skills add qhjqhj00\u002Fresearch-skills-pool --skill azure-ai-openai-dotnet","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-sdk-dotnet__skills__azure-ai-openai-dotnet\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M73JJB6EQPFPPVQK2Y9N67Q0","transformer-lens-interpretability","Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F130-transformer-lens\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M73JHTANRRWEE9HP98TPEHAY","wiki-vitepress","Packages generated wiki Markdown into a VitePress static site with dark theme, dark-mode Mermaid diagrams with click-to-zoom, and production build output. Use when the user wants to create a browsable website from generated wiki pages.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F126-wiki-vitepress\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M73JHJBMVFW46F1Y8K3SBF43","phoenix-observability","Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F124-phoenix\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M73JHFPA3A2806PMP42ZN86Q","frontend-ui-dark-ts","Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F123-frontend-ui-dark-ts\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M73JFVBVK57NRJS49TT2VDCT","tensorboard","Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F113-tensorboard\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M73JFF6PK6ZCN41C89J7HS2B","markdown-mermaid-writing","Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F110-markdown-mermaid-writing\u002FSKILL.md",[],[]]