CtrlK

Community Documentation Log in Get started

tessl/maven-org-springframework-ai--spring-ai-azure-openai

Spring AI integration for Azure OpenAI services providing chat completion, text embeddings, image generation, and audio transcription with GPT, DALL-E, and Whisper models

Overview

Eval results

Files

Spring AI Azure OpenAI

Name: tessl/maven-org-springframework-ai--spring-ai-azure-openai
Author: tessl

Spring AI Azure OpenAI provides integration between Spring AI and Azure OpenAI services. It implements Spring AI's model interfaces for chat completion, text embeddings, image generation, and audio transcription using Azure's OpenAI platform.

Package Information

Package Name: org.springframework.ai:spring-ai-azure-openai
Package Type: Maven
Language: Java
Version: 1.1.2

Installation:

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-azure-openai</artifactId>
    <version>1.1.2</version>
</dependency>

Quick Start

See Quick Start Guide for step-by-step setup instructions.

Core Capabilities

This package provides four main AI model implementations:

Capability	Model Class	Use Case
Chat Completion	`AzureOpenAiChatModel`	Conversational AI with GPT models
Text Embeddings	`AzureOpenAiEmbeddingModel`	Vector embeddings for semantic search
Image Generation	`AzureOpenAiImageModel`	Image creation with DALL-E
Audio Transcription	`AzureOpenAiAudioTranscriptionModel`	Speech-to-text with Whisper

All models support:

Spring Boot autoconfiguration
Micrometer observability
Reactive streaming (where applicable)
Thread-safe concurrent operations

API Overview

Chat Completion

class AzureOpenAiChatModel implements ChatModel {
    ChatResponse call(Prompt prompt);
    Flux<ChatResponse> stream(Prompt prompt);
}

Key Features: Synchronous/streaming responses, tool calling, structured outputs, JSON schema support

Supported Models: gpt-4o, gpt-4, gpt-35-turbo, o1, o3, o4-mini

Full Chat API Reference

Text Embeddings

class AzureOpenAiEmbeddingModel extends AbstractEmbeddingModel {
    EmbeddingResponse call(EmbeddingRequest request);
    float[] embed(Document document);
}

Key Features: Configurable dimensions, batch processing, metadata handling

Supported Models: text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large

Full Embeddings API Reference

Image Generation

class AzureOpenAiImageModel implements ImageModel {
    ImageResponse call(ImagePrompt prompt);
}

Key Features: DALL-E 2/3 support, size/quality/style controls, multiple formats

Supported Models: dall-e-3, dall-e-2

Full Image API Reference

Audio Transcription

class AzureOpenAiAudioTranscriptionModel implements TranscriptionModel {
    AudioTranscriptionResponse call(AudioTranscriptionPrompt prompt);
    String call(Resource audioResource);
}

Key Features: Multiple formats (JSON, SRT, VTT), timestamps, language detection

Supported Models: whisper

Full Audio API Reference

Configuration

Azure OpenAI Client

All models require an OpenAIClient:

OpenAIClient client = new OpenAIClientBuilder()
    .credential(new AzureKeyCredential(apiKey))
    .endpoint(endpoint)
    .buildClient();

Deployment Names

Azure OpenAI uses deployment names instead of model names:

Type	Example Deployments
Chat	gpt-4o, gpt-4, gpt-35-turbo, o1, o3
Embeddings	text-embedding-ada-002, text-embedding-3-small
Images	dall-e-3, dall-e-2
Audio	whisper

Common Patterns

Builder Pattern:

AzureOpenAiChatModel chatModel = AzureOpenAiChatModel.builder()
    .openAIClientBuilder(clientBuilder)
    .defaultOptions(options)
    .observationRegistry(observationRegistry)
    .build();

Options Configuration:

AzureOpenAiChatOptions options = AzureOpenAiChatOptions.builder()
    .deploymentName("gpt-4o")
    .temperature(0.7)
    .maxTokens(1000)
    .build();

Thread Safety

All model classes are fully thread-safe and can handle concurrent requests. Create one instance and reuse it across your application.

Documentation Structure

Guides

Quick Start Guide - Get started in minutes
Integration Patterns - RAG, multi-modal pipelines

Examples

Real-World Scenarios - Production use cases
Edge Cases - Advanced scenarios and error handling

Reference

Chat API Reference - Complete chat completion API
Embeddings API Reference - Complete embeddings API
Image API Reference - Complete image generation API
Audio API Reference - Complete audio transcription API
Error Handling - Exception types and retry patterns
Performance Guide - Optimization and best practices

Quick Reference Tables

Chat Model Parameters

Parameter	Range	Default	Description
temperature	0.0-2.0	0.7	Randomness control
maxTokens	> 0	-	Total token limit (standard models)
maxCompletionTokens	> 0	-	Completion limit (reasoning models)
topP	0.0-1.0	1.0	Nucleus sampling
frequencyPenalty	-2.0-2.0	0.0	Repetition penalty
presencePenalty	-2.0-2.0	0.0	Topic diversity

Embedding Model Dimensions

Model	Default	Configurable	Max Input
text-embedding-ada-002	1536	No	8191 tokens
text-embedding-3-small	1536	Yes (up to 1536)	8191 tokens
text-embedding-3-large	3072	Yes (up to 3072)	8191 tokens

Image Model Sizes

Model	Supported Sizes
DALL-E 3	1024×1024, 1792×1024, 1024×1792
DALL-E 2	256×256, 512×512, 1024×1024

Audio Formats

Format	Extension	Quality	Use Case
mp3	.mp3	Good	General purpose
wav	.wav	Excellent	Best quality
m4a	.m4a	Good	Mobile recordings
webm	.webm	Good	Web recordings

File Limit: 25 MB maximum

Common Imports

// Chat
import org.springframework.ai.azure.openai.AzureOpenAiChatModel;
import org.springframework.ai.azure.openai.AzureOpenAiChatOptions;

// Embeddings
import org.springframework.ai.azure.openai.AzureOpenAiEmbeddingModel;
import org.springframework.ai.azure.openai.AzureOpenAiEmbeddingOptions;

// Images
import org.springframework.ai.azure.openai.AzureOpenAiImageModel;
import org.springframework.ai.azure.openai.AzureOpenAiImageOptions;

// Audio
import org.springframework.ai.azure.openai.AzureOpenAiAudioTranscriptionModel;
import org.springframework.ai.azure.openai.AzureOpenAiAudioTranscriptionOptions;

// Azure Client
import com.azure.ai.openai.OpenAIClient;
import com.azure.ai.openai.OpenAIClientBuilder;
import com.azure.core.credential.AzureKeyCredential;

Utility Classes

MergeUtils

Utility for merging chat completion responses in streaming scenarios.

class MergeUtils {
    static ChatCompletions emptyChatCompletions();
    static ChatCompletions mergeChatCompletions(ChatCompletions left, ChatCompletions right);
}

AzureOpenAiRuntimeHints

Provides GraalVM native image compilation hints. Automatically detected by Spring AOT - no manual configuration needed.

class AzureOpenAiRuntimeHints implements RuntimeHintsRegistrar {
    void registerHints(RuntimeHints hints, ClassLoader classLoader);
}

Package Organization

org.springframework.ai.azure.openai
├── AzureOpenAiChatModel
├── AzureOpenAiChatOptions
├── AzureOpenAiResponseFormat
├── AzureOpenAiEmbeddingModel
├── AzureOpenAiEmbeddingOptions
├── AzureOpenAiImageModel
├── AzureOpenAiImageOptions
├── AzureOpenAiAudioTranscriptionModel
├── AzureOpenAiAudioTranscriptionOptions
├── MergeUtils
├── metadata/
│   ├── AzureOpenAiAudioTranscriptionResponseMetadata
│   ├── AzureOpenAiImageGenerationMetadata
│   └── AzureOpenAiImageResponseMetadata
└── aot/
    └── AzureOpenAiRuntimeHints

Next Steps

Get Started: Follow the Quick Start Guide
Explore Examples: Check Real-World Scenarios
Deep Dive: Read the API References for detailed documentation
Troubleshoot: See Error Handling Guide for common issues

tessl i tessl/maven-org-springframework-ai--spring-ai-azure-openai@1.1.1

Workspace: tessl
Visibility: Public
Created: 2 days ago
Last updated: 2 days ago
Describes: pkg:maven/org.springframework.ai/spring-ai-azure-openai@1.1.x