Azure Cosmos DB

package com.example.demo;

import io.micrometer.observation.ObservationRegistry;
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.autoconfigure.EnableAutoConfiguration;
import org.springframework.boot.CommandLineRunner;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Lazy;

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

import static org.assertj.core.api.Assertions.assertThat;

@SpringBootApplication
@EnableAutoConfiguration
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);

        // Remove the documents from the vector store
		this.vectorStore.delete(List.of(document1.getId(), document2.getId()));
    }

    @Bean
    public ObservationRegistry observationRegistry() {
        return ObservationRegistry.create();
    }
}

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-starter-vector-store-azure-cosmos-db</artifactId>
</dependency>

Map<String, Object> metadata1 = new HashMap<>();
metadata1.put("country", "UK");
metadata1.put("year", 2021);
metadata1.put("city", "London");

Map<String, Object> metadata2 = new HashMap<>();
metadata2.put("country", "NL");
metadata2.put("year", 2022);
metadata2.put("city", "Amsterdam");

Document document1 = new Document("1", "A document about the UK", this.metadata1);
Document document2 = new Document("2", "A document about the Netherlands", this.metadata2);

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

FilterExpressionBuilder builder = new FilterExpressionBuilder();
List<Document> results = vectorStore.similaritySearch(SearchRequest.builder().query("The World")
    .topK(10)
    .filterExpression((this.builder.in("country", "UK", "NL")).build()).build());

@Bean
public VectorStore vectorStore(ObservationRegistry observationRegistry) {
    // Create the Cosmos DB client
    CosmosAsyncClient cosmosClient = new CosmosClientBuilder()
            .endpoint(System.getenv("COSMOSDB_AI_ENDPOINT"))
            .credential(new DefaultAzureCredentialBuilder().build())
            .userAgentSuffix("SpringAI-CDBNoSQL-VectorStore")
            .gatewayMode()
            .buildAsyncClient();

    // Create and configure the vector store
    return CosmosDBVectorStore.builder(cosmosClient, embeddingModel)
            .databaseName("test-database")
            .containerName("test-container")
            // Configure metadata fields for filtering
            .metadataFields(List.of("country", "year", "city"))
            // Set the partition key path (optional)
            .partitionKeyPath("/id")
            // Configure performance settings
            .vectorStoreThroughput(1000)
            .vectorDimensions(1536)  // Match your embedding model's dimensions
            // Add custom batching strategy (optional)
            .batchingStrategy(new TokenCountBatchingStrategy())
            // Add observation registry for metrics
            .observationRegistry(observationRegistry)
            .build();
}

@Bean
public EmbeddingModel embeddingModel() {
    return new TransformersEmbeddingModel();
}

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-azure-cosmos-db-store</artifactId>
</dependency>

CosmosDBVectorStore vectorStore = context.getBean(CosmosDBVectorStore.class);
Optional<CosmosClient> nativeClient = vectorStore.getNativeClient();

if (nativeClient.isPresent()) {
    CosmosClient client = nativeClient.get();
    // Use the native client for Azure Cosmos DB-specific operations
}