diff --git a/yudao-module-ai/yudao-module-ai-biz/src/main/java/cn/iocoder/yudao/module/ai/service/model/AiModelServiceImpl.java b/yudao-module-ai/yudao-module-ai-biz/src/main/java/cn/iocoder/yudao/module/ai/service/model/AiModelServiceImpl.java index d6649a4b36..b73567a1c5 100644 --- a/yudao-module-ai/yudao-module-ai-biz/src/main/java/cn/iocoder/yudao/module/ai/service/model/AiModelServiceImpl.java +++ b/yudao-module-ai/yudao-module-ai-biz/src/main/java/cn/iocoder/yudao/module/ai/service/model/AiModelServiceImpl.java @@ -17,7 +17,7 @@ import org.springframework.ai.chat.model.ChatModel; import org.springframework.ai.embedding.EmbeddingModel; import org.springframework.ai.image.ImageModel; import org.springframework.ai.vectorstore.VectorStore; -import org.springframework.ai.vectorstore.qdrant.QdrantVectorStore; +import org.springframework.ai.vectorstore.milvus.MilvusVectorStore; import org.springframework.stereotype.Service; import org.springframework.validation.annotation.Validated; @@ -114,8 +114,7 @@ public class AiModelServiceImpl implements AiModelService { } @Override - public List getModelListByStatusAndType(Integer status, Integer type, - String platform) { + public List getModelListByStatusAndType(Integer status, Integer type, String platform) { return modelMapper.selectListByStatusAndType(status, type, platform); } @@ -163,9 +162,10 @@ public class AiModelServiceImpl implements AiModelService { platform, apiKey.getApiKey(), apiKey.getUrl(), model.getModel()); // 创建或获取 VectorStore 对象 -// return modelFactory.getOrCreateVectorStore(SimpleVectorStore.class, embeddingModel, metadataFields); - return modelFactory.getOrCreateVectorStore(QdrantVectorStore.class, embeddingModel, metadataFields); -// return modelFactory.getOrCreateVectorStore(RedisVectorStore.class, embeddingModel, metadataFields); + // return modelFactory.getOrCreateVectorStore(SimpleVectorStore.class, embeddingModel, metadataFields); + // return modelFactory.getOrCreateVectorStore(QdrantVectorStore.class, embeddingModel, metadataFields); + // return modelFactory.getOrCreateVectorStore(RedisVectorStore.class, embeddingModel, metadataFields); + return modelFactory.getOrCreateVectorStore(MilvusVectorStore.class, embeddingModel, metadataFields); } } \ No newline at end of file diff --git a/yudao-module-ai/yudao-spring-boot-starter-ai/pom.xml b/yudao-module-ai/yudao-spring-boot-starter-ai/pom.xml index ffcf3941e9..2d1a0af3aa 100644 --- a/yudao-module-ai/yudao-spring-boot-starter-ai/pom.xml +++ b/yudao-module-ai/yudao-spring-boot-starter-ai/pom.xml @@ -70,7 +70,6 @@ ${spring-ai.groupId} spring-ai-qdrant-store ${spring-ai.version} - diff --git a/yudao-module-ai/yudao-spring-boot-starter-ai/src/main/java/cn/iocoder/yudao/framework/ai/config/YudaoAiAutoConfiguration.java b/yudao-module-ai/yudao-spring-boot-starter-ai/src/main/java/cn/iocoder/yudao/framework/ai/config/YudaoAiAutoConfiguration.java index 38e6eb2e33..bea8e5bc0d 100644 --- a/yudao-module-ai/yudao-spring-boot-starter-ai/src/main/java/cn/iocoder/yudao/framework/ai/config/YudaoAiAutoConfiguration.java +++ b/yudao-module-ai/yudao-spring-boot-starter-ai/src/main/java/cn/iocoder/yudao/framework/ai/config/YudaoAiAutoConfiguration.java @@ -11,8 +11,12 @@ import cn.iocoder.yudao.framework.ai.core.model.siliconflow.SiliconFlowChatModel import cn.iocoder.yudao.framework.ai.core.model.suno.api.SunoApi; import cn.iocoder.yudao.framework.ai.core.model.xinghuo.XingHuoChatModel; import lombok.extern.slf4j.Slf4j; +import org.springframework.ai.autoconfigure.vectorstore.milvus.MilvusServiceClientProperties; +import org.springframework.ai.autoconfigure.vectorstore.milvus.MilvusVectorStoreProperties; import org.springframework.ai.autoconfigure.vectorstore.qdrant.QdrantVectorStoreProperties; import org.springframework.ai.autoconfigure.vectorstore.redis.RedisVectorStoreProperties; +import org.springframework.ai.embedding.BatchingStrategy; +import org.springframework.ai.embedding.TokenCountBatchingStrategy; import org.springframework.ai.openai.OpenAiChatModel; import org.springframework.ai.openai.OpenAiChatOptions; import org.springframework.ai.openai.api.OpenAiApi; @@ -22,7 +26,6 @@ import org.springframework.boot.autoconfigure.AutoConfiguration; import org.springframework.boot.autoconfigure.condition.ConditionalOnProperty; import org.springframework.boot.context.properties.EnableConfigurationProperties; import org.springframework.context.annotation.Bean; -import org.springframework.context.annotation.Lazy; /** * 芋道 AI 自动配置 @@ -33,6 +36,7 @@ import org.springframework.context.annotation.Lazy; @EnableConfigurationProperties({YudaoAiProperties.class, QdrantVectorStoreProperties.class, // 解析 Qdrant 配置 RedisVectorStoreProperties.class, // 解析 Redis 配置 + MilvusVectorStoreProperties.class, MilvusServiceClientProperties.class // 解析 Milvus 配置 }) @Slf4j public class YudaoAiAutoConfiguration { @@ -193,18 +197,16 @@ public class YudaoAiAutoConfiguration { return new SunoApi(yudaoAiProperties.getSuno().getBaseUrl()); } - // ========== rag 相关 ========== - // TODO @xin 免费版本 -// @Bean -// @Lazy // TODO 芋艿：临时注释，避免无法启动」 -// public TransformersEmbeddingModel transformersEmbeddingClient() { -// return new TransformersEmbeddingModel(MetadataMode.EMBED); -// } + // ========== RAG 相关 ========== @Bean - @Lazy // TODO 芋艿：临时注释，避免无法启动 public TokenCountEstimator tokenCountEstimator() { return new JTokkitTokenCountEstimator(); } + @Bean + public BatchingStrategy batchingStrategy() { + return new TokenCountBatchingStrategy(); + } + } \ No newline at end of file diff --git a/yudao-module-ai/yudao-spring-boot-starter-ai/src/main/java/cn/iocoder/yudao/framework/ai/core/factory/AiModelFactoryImpl.java b/yudao-module-ai/yudao-spring-boot-starter-ai/src/main/java/cn/iocoder/yudao/framework/ai/core/factory/AiModelFactoryImpl.java index f7c77c45b8..7953157009 100644 --- a/yudao-module-ai/yudao-spring-boot-starter-ai/src/main/java/cn/iocoder/yudao/framework/ai/core/factory/AiModelFactoryImpl.java +++ b/yudao-module-ai/yudao-spring-boot-starter-ai/src/main/java/cn/iocoder/yudao/framework/ai/core/factory/AiModelFactoryImpl.java @@ -5,7 +5,6 @@ import cn.hutool.core.lang.Assert; import cn.hutool.core.lang.Singleton; import cn.hutool.core.lang.func.Func0; import cn.hutool.core.util.ArrayUtil; -import cn.hutool.core.util.ReflectUtil; import cn.hutool.core.util.RuntimeUtil; import cn.hutool.core.util.StrUtil; import cn.hutool.extra.spring.SpringUtil; @@ -29,6 +28,7 @@ import com.alibaba.cloud.ai.dashscope.embedding.DashScopeEmbeddingOptions; import com.alibaba.cloud.ai.dashscope.image.DashScopeImageModel; import com.azure.ai.openai.OpenAIClientBuilder; import io.micrometer.observation.ObservationRegistry; +import io.milvus.client.MilvusServiceClient; import io.qdrant.client.QdrantClient; import io.qdrant.client.QdrantGrpcClient; import lombok.SneakyThrows; @@ -38,6 +38,10 @@ import org.springframework.ai.autoconfigure.azure.openai.AzureOpenAiConnectionPr import org.springframework.ai.autoconfigure.ollama.OllamaAutoConfiguration; import org.springframework.ai.autoconfigure.openai.OpenAiAutoConfiguration; import org.springframework.ai.autoconfigure.qianfan.QianFanAutoConfiguration; +import org.springframework.ai.autoconfigure.vectorstore.milvus.MilvusServiceClientConnectionDetails; +import org.springframework.ai.autoconfigure.vectorstore.milvus.MilvusServiceClientProperties; +import org.springframework.ai.autoconfigure.vectorstore.milvus.MilvusVectorStoreAutoConfiguration; +import org.springframework.ai.autoconfigure.vectorstore.milvus.MilvusVectorStoreProperties; import org.springframework.ai.autoconfigure.vectorstore.qdrant.QdrantVectorStoreAutoConfiguration; import org.springframework.ai.autoconfigure.vectorstore.qdrant.QdrantVectorStoreProperties; import org.springframework.ai.autoconfigure.vectorstore.redis.RedisVectorStoreAutoConfiguration; @@ -47,6 +51,7 @@ import org.springframework.ai.autoconfigure.zhipuai.ZhiPuAiConnectionProperties; import org.springframework.ai.azure.openai.AzureOpenAiChatModel; import org.springframework.ai.chat.model.ChatModel; import org.springframework.ai.document.MetadataMode; +import org.springframework.ai.embedding.BatchingStrategy; import org.springframework.ai.embedding.EmbeddingModel; import org.springframework.ai.image.ImageModel; import org.springframework.ai.ollama.OllamaChatModel; @@ -66,6 +71,7 @@ import org.springframework.ai.stabilityai.StabilityAiImageModel; import org.springframework.ai.stabilityai.api.StabilityAiApi; import org.springframework.ai.vectorstore.SimpleVectorStore; import org.springframework.ai.vectorstore.VectorStore; +import org.springframework.ai.vectorstore.milvus.MilvusVectorStore; import org.springframework.ai.vectorstore.observation.DefaultVectorStoreObservationConvention; import org.springframework.ai.vectorstore.observation.VectorStoreObservationConvention; import org.springframework.ai.vectorstore.qdrant.QdrantVectorStore; @@ -247,6 +253,9 @@ public class AiModelFactoryImpl implements AiModelFactory { if (type == RedisVectorStore.class) { return buildRedisVectorStore(embeddingModel, metadataFields); } + if (type == MilvusVectorStore.class) { + return buildMilvusVectorStore(embeddingModel); + } throw new IllegalArgumentException(StrUtil.format("未知类型({})", type)); }); } @@ -482,8 +491,7 @@ public class AiModelFactoryImpl implements AiModelFactory { QdrantClient qdrantClient = new QdrantClient(grpcClientBuilder.build()); // 创建 QdrantVectorStore 对象 QdrantVectorStore vectorStore = configuration.vectorStore(embeddingModel, properties, qdrantClient, - getObservationRegistry(), getCustomObservationConvention(), - ReflectUtil.invoke(configuration, "batchingStrategy")); + getObservationRegistry(), getCustomObservationConvention(), getBatchingStrategy()); // 初始化索引 vectorStore.afterPropertiesSet(); return vectorStore; @@ -516,13 +524,48 @@ public class AiModelFactoryImpl implements AiModelFactory { })) .observationRegistry(getObservationRegistry().getObject()) .customObservationConvention(getCustomObservationConvention().getObject()) - .batchingStrategy(ReflectUtil.invoke(configuration, "batchingStrategy")) + .batchingStrategy(getBatchingStrategy()) .build(); // 初始化索引 redisVectorStore.afterPropertiesSet(); return redisVectorStore; } + /** + * 参考 {@link MilvusVectorStoreAutoConfiguration} 的 vectorStore 方法 + */ + @SneakyThrows + private MilvusVectorStore buildMilvusVectorStore(EmbeddingModel embeddingModel) { + MilvusVectorStoreAutoConfiguration configuration = new MilvusVectorStoreAutoConfiguration(); + // 获取配置属性 + MilvusVectorStoreProperties serverProperties = SpringUtil.getBean(MilvusVectorStoreProperties.class); + MilvusServiceClientProperties clientProperties = SpringUtil.getBean(MilvusServiceClientProperties.class); + + // 创建 MilvusServiceClient 对象 + MilvusServiceClient milvusClient = configuration.milvusClient(serverProperties, clientProperties, + new MilvusServiceClientConnectionDetails() { + + @Override + public String getHost() { + return clientProperties.getHost(); + } + + @Override + public int getPort() { + return clientProperties.getPort(); + } + + } + ); + // 创建 MilvusVectorStore 对象 + MilvusVectorStore vectorStore = configuration.vectorStore(milvusClient, embeddingModel, serverProperties, + getBatchingStrategy(), getObservationRegistry(), getCustomObservationConvention()); + + // 初始化索引 + vectorStore.afterPropertiesSet(); + return vectorStore; + } + private static ObjectProvider getObservationRegistry() { return new ObjectProvider<>() { @@ -543,4 +586,8 @@ public class AiModelFactoryImpl implements AiModelFactory { }; } + private static BatchingStrategy getBatchingStrategy() { + return SpringUtil.getBean(BatchingStrategy.class); + } + } diff --git a/yudao-server/src/main/resources/application.yaml b/yudao-server/src/main/resources/application.yaml index 4120a73467..419fab471b 100644 --- a/yudao-server/src/main/resources/application.yaml +++ b/yudao-server/src/main/resources/application.yaml @@ -157,8 +157,13 @@ spring: collection-name: knowledge_segment # Qdrant 中向量集合的名称：用于存储向量数据的集合标识符，所有相关的向量操作都会在这个集合中进行 host: 127.0.0.1 port: 6334 - use-tls: false - api-key: + milvus: + initialize-schema: true + database-name: default # Milvus 中数据库的名称 + collection-name: knowledge_segment # Milvus 中集合的名称：用于存储向量数据的集合标识符，所有相关的向量操作都会在这个集合中进行 + client: + host: 127.0.0.1 + port: 19530 qianfan: # 文心一言 api-key: x0cuLZ7XsaTCU08vuJWO87Lg secret-key: R9mYF9dl9KASgi5RUq0FQt3wRisSnOcK