聊聊Spring AI的MilvusVectorStore

本文主要研究一下Spring AI的MilvusVectorStore

示例

pom.xml

复制代码
		<dependency>
			<groupId>org.springframework.ai</groupId>
			<artifactId>spring-ai-starter-vector-store-milvus</artifactId>
		</dependency>

配置

复制代码
spring:
  ai:
    vectorstore:
      milvus:
        initialize-schema: true
        databaseName: "default"
        collectionName: "test_collection1"
        embeddingDimension: 1024
        indexType: IVF_FLAT
        metricType: COSINE
        client:
          host: "localhost"
          port: 19530

代码

复制代码
    @Test
    public void testAddAndSearch() {
        List <Document> documents = List.of(
                new Document("Spring AI rocks!! Spring AI rocks!! Spring AI rocks!! Spring AI rocks!! Spring AI rocks!!", Map.of("meta1", "meta1")),
                new Document("The World is Big and Salvation Lurks Around the Corner"),
                new Document("You walk forward facing the past and you turn back toward the future.", Map.of("meta2", "meta2")));

        // Add the documents to Milvus Vector Store
        vectorStore.add(documents);

        // Retrieve documents similar to a query
        List<Document> results = this.vectorStore.similaritySearch(SearchRequest.builder().query("Spring").topK(5).build());
        log.info("results:{}", JSON.toJSONString(results));
    }

输出如下:

复制代码
results:[{"contentFormatter":{"excludedEmbedMetadataKeys":[],"excludedInferenceMetadataKeys":[],"metadataSeparator":"\n","metadataTemplate":"{key}: {value}","textTemplate":"{metadata_string}\n\n{content}"},"formattedContent":"distance: 0.43509113788604736\nmeta1: meta1\n\nSpring AI rocks!! Spring AI rocks!! Spring AI rocks!! Spring AI rocks!! Spring AI rocks!!","id":"d1c92394-77c8-4c67-9817-0980ad31479d","metadata":{"distance":0.43509113788604736,"meta1":"meta1"},"score":0.5649088621139526,"text":"Spring AI rocks!! Spring AI rocks!! Spring AI rocks!! Spring AI rocks!! Spring AI rocks!!"},{"contentFormatter":{"$ref":"$[0].contentFormatter"},"formattedContent":"distance: 0.5709311962127686\n\nThe World is Big and Salvation Lurks Around the Corner","id":"65d7ddb3-a735-4dad-9da0-cbba5665b149","metadata":{"distance":0.5709311962127686},"score":0.42906883358955383,"text":"The World is Big and Salvation Lurks Around the Corner"},{"contentFormatter":{"$ref":"$[0].contentFormatter"},"formattedContent":"distance: 0.5936022996902466\nmeta2: meta2\n\nYou walk forward facing the past and you turn back toward the future.","id":"26050d78-3396-4b61-97ea-111249f6d037","metadata":{"distance":0.5936022996902466,"meta2":"meta2"},"score":0.40639767050743103,"text":"You walk forward facing the past and you turn back toward the future."}]

源码

MilvusVectorStoreAutoConfiguration

org/springframework/ai/vectorstore/milvus/autoconfigure/MilvusVectorStoreAutoConfiguration.java

复制代码
@AutoConfiguration
@ConditionalOnClass({ MilvusVectorStore.class, EmbeddingModel.class })
@EnableConfigurationProperties({ MilvusServiceClientProperties.class, MilvusVectorStoreProperties.class })
@ConditionalOnProperty(name = SpringAIVectorStoreTypes.TYPE, havingValue = SpringAIVectorStoreTypes.MILVUS,
		matchIfMissing = true)
public class MilvusVectorStoreAutoConfiguration {

	@Bean
	@ConditionalOnMissingBean(MilvusServiceClientConnectionDetails.class)
	PropertiesMilvusServiceClientConnectionDetails milvusServiceClientConnectionDetails(
			MilvusServiceClientProperties properties) {
		return new PropertiesMilvusServiceClientConnectionDetails(properties);
	}

	@Bean
	@ConditionalOnMissingBean(BatchingStrategy.class)
	BatchingStrategy milvusBatchingStrategy() {
		return new TokenCountBatchingStrategy();
	}

	@Bean
	@ConditionalOnMissingBean
	public MilvusVectorStore vectorStore(MilvusServiceClient milvusClient, EmbeddingModel embeddingModel,
			MilvusVectorStoreProperties properties, BatchingStrategy batchingStrategy,
			ObjectProvider<ObservationRegistry> observationRegistry,
			ObjectProvider<VectorStoreObservationConvention> customObservationConvention) {

		return MilvusVectorStore.builder(milvusClient, embeddingModel)
			.initializeSchema(properties.isInitializeSchema())
			.databaseName(properties.getDatabaseName())
			.collectionName(properties.getCollectionName())
			.embeddingDimension(properties.getEmbeddingDimension())
			.indexType(IndexType.valueOf(properties.getIndexType().name()))
			.metricType(MetricType.valueOf(properties.getMetricType().name()))
			.indexParameters(properties.getIndexParameters())
			.iDFieldName(properties.getIdFieldName())
			.autoId(properties.isAutoId())
			.contentFieldName(properties.getContentFieldName())
			.metadataFieldName(properties.getMetadataFieldName())
			.embeddingFieldName(properties.getEmbeddingFieldName())
			.batchingStrategy(batchingStrategy)
			.observationRegistry(observationRegistry.getIfUnique(() -> ObservationRegistry.NOOP))
			.customObservationConvention(customObservationConvention.getIfAvailable(() -> null))
			.build();
	}

	@Bean
	@ConditionalOnMissingBean
	public MilvusServiceClient milvusClient(MilvusVectorStoreProperties serverProperties,
			MilvusServiceClientProperties clientProperties, MilvusServiceClientConnectionDetails connectionDetails) {

		var builder = ConnectParam.newBuilder()
			.withHost(connectionDetails.getHost())
			.withPort(connectionDetails.getPort())
			.withDatabaseName(serverProperties.getDatabaseName())
			.withConnectTimeout(clientProperties.getConnectTimeoutMs(), TimeUnit.MILLISECONDS)
			.withKeepAliveTime(clientProperties.getKeepAliveTimeMs(), TimeUnit.MILLISECONDS)
			.withKeepAliveTimeout(clientProperties.getKeepAliveTimeoutMs(), TimeUnit.MILLISECONDS)
			.withRpcDeadline(clientProperties.getRpcDeadlineMs(), TimeUnit.MILLISECONDS)
			.withSecure(clientProperties.isSecure())
			.withIdleTimeout(clientProperties.getIdleTimeoutMs(), TimeUnit.MILLISECONDS)
			.withAuthorization(clientProperties.getUsername(), clientProperties.getPassword());

		if (clientProperties.isSecure() && StringUtils.hasText(clientProperties.getUri())) {
			builder.withUri(clientProperties.getUri());
		}

		if (clientProperties.isSecure() && StringUtils.hasText(clientProperties.getToken())) {
			builder.withToken(clientProperties.getToken());
		}

		if (clientProperties.isSecure() && StringUtils.hasText(clientProperties.getClientKeyPath())) {
			builder.withClientKeyPath(clientProperties.getClientKeyPath());
		}

		if (clientProperties.isSecure() && StringUtils.hasText(clientProperties.getClientPemPath())) {
			builder.withClientPemPath(clientProperties.getClientPemPath());
		}

		if (clientProperties.isSecure() && StringUtils.hasText(clientProperties.getCaPemPath())) {
			builder.withCaPemPath(clientProperties.getCaPemPath());
		}

		if (clientProperties.isSecure() && StringUtils.hasText(clientProperties.getServerPemPath())) {
			builder.withServerPemPath(clientProperties.getServerPemPath());
		}

		if (clientProperties.isSecure() && StringUtils.hasText(clientProperties.getServerName())) {
			builder.withServerName(clientProperties.getServerName());
		}

		return new MilvusServiceClient(builder.build());
	}

	static class PropertiesMilvusServiceClientConnectionDetails implements MilvusServiceClientConnectionDetails {

		private final MilvusServiceClientProperties properties;

		PropertiesMilvusServiceClientConnectionDetails(MilvusServiceClientProperties properties) {
			this.properties = properties;
		}

		@Override
		public String getHost() {
			return this.properties.getHost();
		}

		@Override
		public int getPort() {
			return this.properties.getPort();
		}

	}

}

MilvusVectorStoreAutoConfiguration在spring.ai.vectorstore.typemilvus会启用(matchIfMissing=true),它根据MilvusServiceClientProperties创建PropertiesMilvusServiceClientConnectionDetails,创建TokenCountBatchingStrategy、MilvusServiceClient,最后根据MilvusVectorStoreProperties创建MilvusVectorStore

MilvusServiceClientProperties

org/springframework/ai/vectorstore/milvus/autoconfigure/MilvusServiceClientProperties.java

复制代码
@ConfigurationProperties(MilvusServiceClientProperties.CONFIG_PREFIX)
public class MilvusServiceClientProperties {

	public static final String CONFIG_PREFIX = "spring.ai.vectorstore.milvus.client";

	/**
	 * Secure the authorization for this connection, set to True to enable TLS.
	 */
	protected boolean secure = false;

	/**
	 * Milvus host name/address.
	 */
	private String host = "localhost";

	/**
	 * Milvus the connection port. Value must be greater than zero and less than 65536.
	 */
	private int port = 19530;

	/**
	 * The uri of Milvus instance
	 */
	private String uri;

	/**
	 * Token serving as the key for identification and authentication purposes.
	 */
	private String token;

	/**
	 * Connection timeout value of client channel. The timeout value must be greater than
	 * zero.
	 */
	private long connectTimeoutMs = 10000;

	/**
	 * Keep-alive time value of client channel. The keep-alive value must be greater than
	 * zero.
	 */
	private long keepAliveTimeMs = 55000;

	/**
	 * Enables the keep-alive function for client channel.
	 */
	// private boolean keepAliveWithoutCalls = false;

	/**
	 * The keep-alive timeout value of client channel. The timeout value must be greater
	 * than zero.
	 */
	private long keepAliveTimeoutMs = 20000;

	/**
	 * Deadline for how long you are willing to wait for a reply from the server. With a
	 * deadline setting, the client will wait when encounter fast RPC fail caused by
	 * network fluctuations. The deadline value must be larger than or equal to zero.
	 * Default value is 0, deadline is disabled.
	 */
	private long rpcDeadlineMs = 0; // Disabling deadline

	/**
	 * The client.key path for tls two-way authentication, only takes effect when "secure"
	 * is True.
	 */
	private String clientKeyPath;

	/**
	 * The client.pem path for tls two-way authentication, only takes effect when "secure"
	 * is True.
	 */
	private String clientPemPath;

	/**
	 * The ca.pem path for tls two-way authentication, only takes effect when "secure" is
	 * True.
	 */
	private String caPemPath;

	/**
	 * server.pem path for tls one-way authentication, only takes effect when "secure" is
	 * True.
	 */
	private String serverPemPath;

	/**
	 * Sets the target name override for SSL host name checking, only takes effect when
	 * "secure" is True. Note: this value is passed to grpc.ssl_target_name_override
	 */
	private String serverName;

	/**
	 * Idle timeout value of client channel. The timeout value must be larger than zero.
	 */
	private long idleTimeoutMs = TimeUnit.MILLISECONDS.convert(24, TimeUnit.HOURS);

	/**
	 * The username and password for this connection.
	 */
	private String username = "root";

	/**
	 * The password for this connection.
	 */
	private String password = "milvus";

	//......
}	

MilvusServiceClientProperties提供了spring.ai.vectorstore.milvus.client的配置,可以设置host、port、connectTimeoutMs、username、password等

PropertiesMilvusServiceClientConnectionDetails

org/springframework/ai/vectorstore/milvus/autoconfigure/MilvusVectorStoreAutoConfiguration.java

复制代码
	static class PropertiesMilvusServiceClientConnectionDetails implements MilvusServiceClientConnectionDetails {

		private final MilvusServiceClientProperties properties;

		PropertiesMilvusServiceClientConnectionDetails(MilvusServiceClientProperties properties) {
			this.properties = properties;
		}

		@Override
		public String getHost() {
			return this.properties.getHost();
		}

		@Override
		public int getPort() {
			return this.properties.getPort();
		}

	}

PropertiesMilvusServiceClientConnectionDetails实现了MilvusServiceClientConnectionDetails接口,适配了getHost、getPort方法

MilvusVectorStoreProperties

org/springframework/ai/vectorstore/milvus/autoconfigure/MilvusVectorStoreProperties.java

复制代码
@ConfigurationProperties(MilvusVectorStoreProperties.CONFIG_PREFIX)
public class MilvusVectorStoreProperties extends CommonVectorStoreProperties {

	public static final String CONFIG_PREFIX = "spring.ai.vectorstore.milvus";

	/**
	 * The name of the Milvus database to connect to.
	 */
	private String databaseName = MilvusVectorStore.DEFAULT_DATABASE_NAME;

	/**
	 * Milvus collection name to store the vectors.
	 */
	private String collectionName = MilvusVectorStore.DEFAULT_COLLECTION_NAME;

	/**
	 * The dimension of the vectors to be stored in the Milvus collection.
	 */
	private int embeddingDimension = MilvusVectorStore.OPENAI_EMBEDDING_DIMENSION_SIZE;

	/**
	 * The type of the index to be created for the Milvus collection.
	 */
	private MilvusIndexType indexType = MilvusIndexType.IVF_FLAT;

	/**
	 * The metric type to be used for the Milvus collection.
	 */
	private MilvusMetricType metricType = MilvusMetricType.COSINE;

	/**
	 * The index parameters to be used for the Milvus collection.
	 */
	private String indexParameters = "{\"nlist\":1024}";

	/**
	 * The ID field name for the collection.
	 */
	private String idFieldName = MilvusVectorStore.DOC_ID_FIELD_NAME;

	/**
	 * Boolean flag to indicate if the auto-id is used.
	 */
	private boolean isAutoId = false;

	/**
	 * The content field name for the collection.
	 */
	private String contentFieldName = MilvusVectorStore.CONTENT_FIELD_NAME;

	/**
	 * The metadata field name for the collection.
	 */
	private String metadataFieldName = MilvusVectorStore.METADATA_FIELD_NAME;

	/**
	 * The embedding field name for the collection.
	 */
	private String embeddingFieldName = MilvusVectorStore.EMBEDDING_FIELD_NAME;

	//......

	public enum MilvusMetricType {

		/**
		 * Invalid metric type
		 */
		INVALID,
		/**
		 * Euclidean distance
		 */
		L2,
		/**
		 * Inner product
		 */
		IP,
		/**
		 * Cosine distance
		 */
		COSINE,
		/**
		 * Hamming distance
		 */
		HAMMING,
		/**
		 * Jaccard distance
		 */
		JACCARD

	}

	public enum MilvusIndexType {

		INVALID, FLAT, IVF_FLAT, IVF_SQ8, IVF_PQ, HNSW, DISKANN, AUTOINDEX, SCANN, GPU_IVF_FLAT, GPU_IVF_PQ, BIN_FLAT,
		BIN_IVF_FLAT, TRIE, STL_SORT

	}

}	

MilvusVectorStoreProperties提供了spring.ai.vectorstore.milvus的配置,主要是配置databaseName、collectionName、embeddingDimension(默认1536)、indexType(默认IVF_FLAT)、metricType(默认COSINE)

CommonVectorStoreProperties

org/springframework/ai/vectorstore/properties/CommonVectorStoreProperties.java

复制代码
public class CommonVectorStoreProperties {

	/**
	 * Vector stores do not initialize schema by default on application startup. The
	 * applications explicitly need to opt-in for initializing the schema on startup. The
	 * recommended way to initialize the schema on startup is to set the initialize-schema
	 * property on the vector store. See {@link #setInitializeSchema(boolean)}.
	 */
	private boolean initializeSchema = false;

	public boolean isInitializeSchema() {
		return this.initializeSchema;
	}

	public void setInitializeSchema(boolean initializeSchema) {
		this.initializeSchema = initializeSchema;
	}

}

CommonVectorStoreProperties定义了initializeSchema属性,代表说是否需要在启动的时候初始化schema

小结

Spring AI提供了spring-ai-starter-vector-store-milvus用于自动装配MilvusVectorStore。要注意的是embeddingDimension默认是1536,如果出现io.milvus.exception.ParamException: Incorrect dimension for field 'embedding': the no.0 vector's dimension: 1024 is not equal to field's dimension: 1536,那么需要重建schema,把embeddingDimension设置为1024。

doc

相关推荐
洛小豆1 小时前
在Java中,Integer.parseInt和Integer.valueOf有什么区别
java·后端·面试
IT_陈寒1 小时前
JavaScript 性能优化:5 个被低估的 V8 引擎技巧让你的代码快 200%
前端·人工智能·后端
Juchecar2 小时前
一文讲清 PyTorch 中反向传播(Backpropagation)的实现原理
人工智能
前端小张同学2 小时前
服务器上如何搭建jenkins 服务CI/CD😎😎
java·后端
黎燃2 小时前
游戏NPC的智能行为设计:从规则驱动到强化学习的演进
人工智能
ytadpole2 小时前
Spring Cloud Gateway:一次不规范 URL 引发的路由转发404问题排查
java·后端
华仔啊2 小时前
基于 RuoYi-Vue 轻松实现单用户登录功能,亲测有效
java·vue.js·后端
机器之心2 小时前
高阶程序,让AI从技术可行到商业可信的最后一公里
人工智能·openai
martinzh2 小时前
解锁RAG高阶密码:自适应、多模态、个性化技术深度剖析
人工智能