feat(ai): 集成 Pinecone 向量数据库并实现知识库 RAG 功能

云

昨天 ad346a7e1f1c35b09a5550c1b60cebe68f0619bf

 src/main/java/com/ruoyi/ai/config/EmbeddingStoreConfig.java

@@ -5,32 +5,48 @@
import dev.langchain4j.store.embedding.EmbeddingStore;
import dev.langchain4j.store.embedding.pinecone.PineconeEmbeddingStore;
import dev.langchain4j.store.embedding.pinecone.PineconeServerlessIndexConfig;
import org.springframework.beans.factory.annotation.Autowired;
import io.pinecone.clients.Index;
import io.pinecone.clients.Pinecone;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;

/**
 * @author :yys
 * @date : 2025/5/2 21:07
 * 向量存储配置
 */
@Configuration
public class EmbeddingStoreConfig {

    @Autowired
    private EmbeddingModel embeddingModel;
    @Value("${pinecone.api-key:pcsk_4SJLnh_tNB3wSLJU8tc4E5P28PcXX8eCLdURqZpVhg1FMV8CRYxjneWdzqRdB5Ftqooi9}")
    private String pineconeApiKey;

    @Value("${pinecone.index:xiaozhi-index}")
    private String indexName;

    @Value("${pinecone.namespace:knowledge-base}")
    private String namespace;

    @Bean
    public EmbeddingStore<TextSegment> embeddingStore() {
        //创建向量存储
    public Pinecone pinecone() {
        return new Pinecone.Builder(pineconeApiKey).build();
    }

    @Bean
    public Index pineconeIndex(Pinecone pinecone) {
        return pinecone.getIndexConnection(indexName);
    }

    @Bean
    public EmbeddingStore<TextSegment> embeddingStore(EmbeddingModel embeddingModel) {
        return PineconeEmbeddingStore.builder()
                .apiKey("pcsk_4SJLnh_tNB3wSLJU8tc4E5P28PcXX8eCLdURqZpVhg1FMV8CRYxjneWdzqRdB5Ftqooi9")
                .index("xiaozhi-index")//如果指定的索引不存在，将创建一个新的索引
                .nameSpace("xiaozhi-namespace") //如果指定的名称空间不存在，将创建一个新的名称 空间
                .apiKey(pineconeApiKey)
                .index(indexName)
                .nameSpace(namespace)
                .createIndex(PineconeServerlessIndexConfig.builder()
                        .cloud("AWS") //指定索引部署在 AWS 云服务上。
                        .region("us-east-1") //指定索引所在的 AWS 区域为 us-east-1。
                        .dimension(embeddingModel.dimension()) //指定索引的向量维度，该维度与 embeddedModel 生成的向量维度相同。
                        .cloud("AWS")
                        .region("us-east-1")
                        .dimension(embeddingModel.dimension())
                        .build())
                .build();
    }
}
}