java.lang.Object

com.tnsai.llm.providers.AzureOpenAIClient

All Implemented Interfaces:: com.tnsai.llm.LLMClient

public class AzureOpenAIClient extends Object implements com.tnsai.llm.LLMClient

Azure OpenAI Service client implementation. Provides access to OpenAI models deployed on Azure infrastructure.

Azure OpenAI differs from OpenAI API in several ways:

Uses deployment-based routing instead of model names
Different endpoint format: https://{resource}.openai.azure.com/openai/deployments/{deployment}/chat/completions
Supports both API key and Azure AD (Entra ID) authentication
Includes Azure-specific content filtering

Configuration via environment variables:

AZURE_OPENAI_API_KEY - API key for authentication
AZURE_OPENAI_ENDPOINT - Resource endpoint (e.g., https://my-resource.openai.azure.com)
AZURE_OPENAI_DEPLOYMENT_ID - Deployment name (model deployment)
AZURE_OPENAI_API_VERSION - API version (default: 2024-08-01-preview)

Usage examples:


 // From environment variables
 var client = AzureOpenAIClient.fromEnv();

 // With explicit API key
 var client = AzureOpenAIClient.withApiKey(
     "https://my-resource.openai.azure.com",
     "your-api-key",
     "gpt-4o-deployment"
 );

 // With Azure AD authentication
 var client = AzureOpenAIClient.withAzureAD(
     "https://my-resource.openai.azure.com",
     "gpt-4o-deployment"
 );

See Also:

Nested Class Summary

Nested Classes

Modifier and Type

Class

Description

static enum

AzureOpenAIClient.AuthType

Authentication type for Azure OpenAI.

static class

AzureOpenAIClient.AzureContentFilterException

Exception thrown when Azure OpenAI content filter rejects the request.
Method Summary

Modifier and Type

Method

Description

com.tnsai.llm.ChatResponse

chat(String message, Optional<String> systemPrompt, Optional<List<Map<String,Object>>> history, Optional<List<Map<String,Object>>> tools)

static AzureOpenAIClient

fromEnv()

Creates an AzureOpenAIClient from environment variables.

static AzureOpenAIClient

fromEnv(float temperature)

Creates an AzureOpenAIClient from environment variables with custom temperature.

static AzureOpenAIClient

fromEnv(float temperature, Float topP, Integer maxTokens)

Creates an AzureOpenAIClient from environment variables with custom temperature, topP, and max tokens.

static AzureOpenAIClient

fromEnv(float temperature, Integer maxTokens)

Creates an AzureOpenAIClient from environment variables with custom temperature and max tokens.

String

getApiVersion()

Returns the API version.

AzureOpenAIClient.AuthType

getAuthType()

Returns the authentication type.

String

getDeploymentId()

Returns the deployment ID.

String

getEndpoint()

Returns the Azure OpenAI endpoint.

Optional<Integer>

getMaxTokens()

String

getModel()

float

getTemperature()

Optional<Float>

getTopP()

Stream<String>

streamChat(String message, Optional<String> systemPrompt, Optional<List<Map<String,Object>>> history, Optional<List<Map<String,Object>>> tools)

static AzureOpenAIClient

withApiKey(String endpoint, String apiKey, String deploymentId)

Creates an AzureOpenAIClient with API key authentication.

static AzureOpenAIClient

withApiKey(String endpoint, String apiKey, String deploymentId, String apiVersion, float temperature, Integer maxTokens)

Creates an AzureOpenAIClient with API key authentication and custom settings.

static AzureOpenAIClient

withAzureAD(String endpoint, String azureAdToken, String deploymentId)

Creates an AzureOpenAIClient with Azure AD (Entra ID) authentication.

static AzureOpenAIClient

withAzureAD(String endpoint, String azureAdToken, String deploymentId, String apiVersion, float temperature, Integer maxTokens)

Creates an AzureOpenAIClient with Azure AD authentication and custom settings.

Methods inherited from class java.lang.Object
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface com.tnsai.llm.LLMClient
chat, chat, chat, chat, chat, getCapabilities, getProviderName, listModels, streamChat, streamChat, streamChatWithHandler, streamChatWithHandler, streamChatWithSpec, streamChatWithSpec

Method Details
- fromEnv
  
  public static AzureOpenAIClient fromEnv()
  Creates an AzureOpenAIClient from environment variables.
  Required environment variables:
  
  AZURE_OPENAI_ENDPOINT - Resource endpoint
  
  AZURE_OPENAI_DEPLOYMENT_ID - Deployment name
  
  AZURE_OPENAI_API_KEY - API key
  
  Optional environment variables:
  
  AZURE_OPENAI_API_VERSION - API version (default: 2024-08-01-preview)
  Returns:
  
  A new AzureOpenAIClient instance
  
  Throws:
  
  IllegalArgumentException - if required environment variables are missing
- fromEnv
  
  public static AzureOpenAIClient fromEnv(float temperature)
  
  Creates an AzureOpenAIClient from environment variables with custom temperature.
  
  Parameters:
  
  temperature - The temperature for response generation
  
  Returns:
  
  A new AzureOpenAIClient instance
- fromEnv
  
  public static AzureOpenAIClient fromEnv(float temperature, Integer maxTokens)
  
  Creates an AzureOpenAIClient from environment variables with custom temperature and max tokens.
  
  Parameters:
  
  temperature - The temperature for response generation
  
  maxTokens - The maximum number of tokens to generate
  
  Returns:
  
  A new AzureOpenAIClient instance
- fromEnv
  
  public static AzureOpenAIClient fromEnv(float temperature, Float topP, Integer maxTokens)
  
  Creates an AzureOpenAIClient from environment variables with custom temperature, topP, and max tokens.
  
  Parameters:
  
  temperature - The temperature for response generation
  
  topP - The top-p (nucleus sampling) value (0.0-1.0, null for default)
  
  maxTokens - The maximum number of tokens to generate
  
  Returns:
  
  A new AzureOpenAIClient instance
- withApiKey
  
  public static AzureOpenAIClient withApiKey(String endpoint, String apiKey, String deploymentId)
  
  Creates an AzureOpenAIClient with API key authentication.
  
  Parameters:
  
  endpoint - The Azure OpenAI resource endpoint
  
  apiKey - The API key
  
  deploymentId - The deployment ID
  
  Returns:
  
  A new AzureOpenAIClient instance
- withApiKey
  
  public static AzureOpenAIClient withApiKey(String endpoint, String apiKey, String deploymentId, String apiVersion, float temperature, Integer maxTokens)
  
  Creates an AzureOpenAIClient with API key authentication and custom settings.
  
  Parameters:
  
  endpoint - The Azure OpenAI resource endpoint
  
  apiKey - The API key
  
  deploymentId - The deployment ID
  
  apiVersion - The API version (null for default)
  
  temperature - The temperature for response generation
  
  maxTokens - The maximum number of tokens to generate
  
  Returns:
  
  A new AzureOpenAIClient instance
- withAzureAD
  
  public static AzureOpenAIClient withAzureAD(String endpoint, String azureAdToken, String deploymentId)
  
  Creates an AzureOpenAIClient with Azure AD (Entra ID) authentication.
  Note: You need to obtain the Azure AD token separately using Azure Identity SDK or other means. The token should have the cognitive services scope.
  
  Parameters:
  
  endpoint - The Azure OpenAI resource endpoint
  
  azureAdToken - The Azure AD bearer token
  
  deploymentId - The deployment ID
  
  Returns:
  
  A new AzureOpenAIClient instance
- withAzureAD
  
  public static AzureOpenAIClient withAzureAD(String endpoint, String azureAdToken, String deploymentId, String apiVersion, float temperature, Integer maxTokens)
  
  Creates an AzureOpenAIClient with Azure AD authentication and custom settings.
  
  Parameters:
  
  endpoint - The Azure OpenAI resource endpoint
  
  azureAdToken - The Azure AD bearer token
  
  deploymentId - The deployment ID
  
  apiVersion - The API version (null for default)
  
  temperature - The temperature for response generation
  
  maxTokens - The maximum number of tokens to generate
  
  Returns:
  
  A new AzureOpenAIClient instance
- getModel
  
  public String getModel()
  
  Specified by:
  
  getModel in interface com.tnsai.llm.LLMClient
- getTemperature
  
  public float getTemperature()
  
  Specified by:
  
  getTemperature in interface com.tnsai.llm.LLMClient
- getTopP
  
  public Optional<Float> getTopP()
  
  Specified by:
  
  getTopP in interface com.tnsai.llm.LLMClient
- getMaxTokens
  
  public Optional<Integer> getMaxTokens()
  
  Specified by:
  
  getMaxTokens in interface com.tnsai.llm.LLMClient
- chat
  
  public com.tnsai.llm.ChatResponse chat(String message, Optional<String> systemPrompt, Optional<List<Map<String,Object>>> history, Optional<List<Map<String,Object>>> tools)
  
  Specified by:
  
  chat in interface com.tnsai.llm.LLMClient
- streamChat
  
  public Stream<String> streamChat(String message, Optional<String> systemPrompt, Optional<List<Map<String,Object>>> history, Optional<List<Map<String,Object>>> tools)
  
  Specified by:
  
  streamChat in interface com.tnsai.llm.LLMClient
- getEndpoint
  
  public String getEndpoint()
  
  Returns the Azure OpenAI endpoint.
  
  Returns:
  
  The endpoint URL
- getDeploymentId
  
  public String getDeploymentId()
  
  Returns the deployment ID.
  
  Returns:
  
  The deployment ID
- getApiVersion
  
  public String getApiVersion()
  
  Returns the API version.
  
  Returns:
  
  The API version
- getAuthType
  
  public AzureOpenAIClient.AuthType getAuthType()
  
  Returns the authentication type.
  
  Returns:
  
  The auth type

Class AzureOpenAIClient

Nested Class Summary

Method Summary

Methods inherited from class java.lang.Object

Methods inherited from interface com.tnsai.llm.LLMClient

Method Details

fromEnv

fromEnv

fromEnv

fromEnv

withApiKey

withApiKey

withAzureAD

withAzureAD

getModel

getTemperature

getTopP

getMaxTokens

chat

streamChat

getEndpoint

getDeploymentId

getApiVersion

getAuthType