AzureOpenAI

Features

• AgentFactory (AzureOpenAIAgentFactory)
• AIToolsFactory integration (tools in AgentOptions.Tools)
• EmbeddingFactory (AzureOpenAIEmbeddingFactory)
• OpenAI-style reasoning settings and ClientType (ChatClient or ResponsesApi)

Package

dotnet add package AgentFrameworkToolkit.AzureOpenAI

Quick start

AzureOpenAIAgentFactory agentFactory = new("<endpoint>", "<apiKey>");
AzureOpenAIAgent agent = agentFactory.CreateAgent(new AgentOptions
{
    Model = "gpt-5",
    ReasoningEffort = OpenAIReasoningEffort.Low,
    Instructions = "You are a nice AI"
});

AgentRunResponse response = await agent.RunAsync("Hello World");
Console.WriteLine(response);

Note

In Azure OpenAI, Model refers to your deployment name, not the model id.

Embeddings

AzureOpenAIEmbeddingFactory embeddingFactory = new("<endpoint>", "<apiKey>");
IEmbeddingGenerator<string, Embedding<float>> generator =
    embeddingFactory.GetEmbeddingGenerator("text-embedding-3-small");
Embedding<float> embedding = await generator.GenerateAsync("Hello");

Connection options

• Endpoint (required)
• ApiKey or Credentials (TokenCredential) for RBAC
• NetworkTimeout
• DefaultClientType
• AutoCorrectFoundryEndpoint (optional, defaults to true)
• AdditionalAzureOpenAIClientOptions

Dependency injection

builder.Services.AddAzureOpenAIAgentFactory("<endpoint>", "<apiKey>");
builder.Services.AddAzureOpenAIAgentFactory(new AzureOpenAIConnection
{
    Endpoint = "<endpoint>",
    ApiKey = "<apiKey>"
});

builder.Services.AddAzureOpenAIEmbeddingFactory("<endpoint>", "<apiKey>");

Notes

• See AgentFactories for shared agent options and middleware.
• See EmbeddingFactories for additional embedding examples.
• See AIToolsFactory for tool creation and MCP support.