Spring AI Cosmos DB Documentation GitHub

Spring AI Azure Cosmos DB

Spring AI integrations for Azure Cosmos DB — bringing the power of Microsoft's globally distributed database to the Spring AI ecosystem.

💡 Tip: These modules work with Spring AI's standard abstractions, so you can swap implementations without changing your application code.

Modules

🗄️ Vector Store

Store document embeddings and perform similarity searches using DiskANN-powered vector indexing.

Azure Cosmos DB

⚙️ Vector Store Auto-Configuration

Zero-config Spring Boot setup for the Cosmos DB Vector Store with sensible defaults.

Spring Boot

💬 Chat Memory

Persistent conversation storage using Cosmos DB for chat history and message retrieval.

Azure Cosmos DB

⚙️ Chat Memory Auto-Configuration

Zero-config Spring Boot setup for the Cosmos DB Chat Memory Repository with sensible defaults.

Spring Boot

Quick Start

1. Add the dependency

<dependency>
    <groupId>com.azure.spring.ai</groupId>
    <artifactId>spring-ai-autoconfigure-vector-store-azure-cosmos-db</artifactId>
    <version>1.0.0-SNAPSHOT</version>
</dependency>

2. Configure your connection

spring.ai.vectorstore.cosmosdb.endpoint=https://your-account.documents.azure.com:443/
spring.ai.vectorstore.cosmosdb.databaseName=my-database
spring.ai.vectorstore.cosmosdb.containerName=my-vectors
spring.ai.vectorstore.cosmosdb.vectorDimensions=1536

3. Inject and use

@Autowired
private VectorStore vectorStore;

// Add documents
vectorStore.add(List.of(new Document("Hello world")));

// Search
List<Document> results = vectorStore.similaritySearch(
    SearchRequest.builder().query("Hello").topK(5).build());

Requirements

Authentication

All modules support two authentication methods: