Azure Cosmos DB Vector Store Auto-Configuration

Spring Boot auto-configuration for the Azure Cosmos DB Vector Store. This module provides zero-config setup when using Spring Boot.

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>

This transitively brings in the spring-ai-azure-cosmos-db-store module.

Configuration Properties

Add these to your application.properties or application.yml:

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.metadataFields=country,year,city
spring.ai.vectorstore.cosmosdb.vectorStoreThroughput=1000
spring.ai.vectorstore.cosmosdb.vectorDimensions=1536
spring.ai.vectorstore.cosmosdb.partitionKeyPath=/id

Authentication

Key-based (set the key property):

spring.ai.vectorstore.cosmosdb.key=your-cosmos-db-key

Azure Identity (recommended for production — omit the key property):

When no key is provided, the auto-configuration uses DefaultAzureCredential for authentication via managed identity, service principal, or other Azure credential sources.

Usage

Once configured, simply inject VectorStore:

import org.springframework.ai.vectorstore.VectorStore;
import org.springframework.beans.factory.annotation.Autowired;

@Autowired
private VectorStore vectorStore;

Example Application

package com.example.demo;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.ai.document.Document;
import org.springframework.ai.vectorstore.SearchRequest;
import org.springframework.ai.vectorstore.VectorStore;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.CommandLineRunner;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import org.springframework.context.annotation.Lazy;

import java.util.List;
import java.util.Map;
import java.util.UUID;

@SpringBootApplication
public class DemoApplication implements CommandLineRunner {

    private static final Logger log = LoggerFactory.getLogger(DemoApplication.class);

    @Lazy
    @Autowired
    private VectorStore vectorStore;

    public static void main(String[] args) {
        SpringApplication.run(DemoApplication.class, args);
    }

    @Override
    public void run(String... args) throws Exception {
        Document document1 = new Document(UUID.randomUUID().toString(),
            "Sample content1", Map.of("key1", "value1"));
        Document document2 = new Document(UUID.randomUUID().toString(),
            "Sample content2", Map.of("key2", "value2"));

        this.vectorStore.add(List.of(document1, document2));

        List<Document> results = this.vectorStore.similaritySearch(
            SearchRequest.builder().query("Sample content").topK(1).build());
        log.info("Search results: {}", results);

        this.vectorStore.delete(List.of(document1.getId(), document2.getId()));
    }
}

Full Property Reference

Manual Configuration

If you prefer to configure the vector store manually (without auto-configuration), see the Vector Store page.