AI智能工牌的建表语句

src/main/java/com/rj/embedding/EnbedingModelConfig.java

@@ -0,0 +1,122 @@
+package com.rj.embedding;
+
+import dev.langchain4j.community.store.embedding.redis.RedisEmbeddingStore;
+import dev.langchain4j.data.document.Document;
+import dev.langchain4j.data.document.DocumentSplitter;
+import dev.langchain4j.data.document.loader.ClassPathDocumentLoader;
+import dev.langchain4j.data.document.loader.FileSystemDocumentLoader;
+import dev.langchain4j.data.document.parser.apache.pdfbox.ApachePdfBoxDocumentParser;
+import dev.langchain4j.data.document.splitter.DocumentSplitters;
+import dev.langchain4j.data.segment.TextSegment;
+import dev.langchain4j.model.embedding.EmbeddingModel;
+import dev.langchain4j.rag.content.retriever.ContentRetriever;
+import dev.langchain4j.rag.content.retriever.EmbeddingStoreContentRetriever;
+import dev.langchain4j.store.embedding.EmbeddingStore;
+import dev.langchain4j.store.embedding.EmbeddingStoreIngestor;
+import dev.langchain4j.store.embedding.inmemory.InMemoryEmbeddingStore;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.beans.factory.annotation.Qualifier;
+import org.springframework.context.annotation.Bean;
+import org.springframework.context.annotation.Configuration;
+import org.springframework.context.annotation.Primary;
+
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
+import java.util.ArrayList;
+import java.util.List;
+
+import java.util.List;
+
+/**
+ * Author: 李中华  wx: spllzh  email(qq): 28668817@qq.com
+ * Date: 2025/8/4 18:21
+ **/
+@Configuration
+public class EnbedingModelConfig {
+
+
+    @Autowired
+    private EmbeddingModel embeddingModel;
+
+    @Autowired
+    RedisEmbeddingStore redisEmbeddingStore;
+    /**
+     * 创建向量数据库操作对象
+     * @return
+     */
+    @Bean("myEmbeddingStoreInMemory")
+//    @Primary
+    public EmbeddingStore embeddingStoreInMemory() {
+        //1 , 加载知识库文档进 内存
+        List<Document> documents = ClassPathDocumentLoader.loadDocuments("knowledge");
+        //2 ， 构建向量数据库操作对象
+        InMemoryEmbeddingStore<TextSegment> embeddingStore = new InMemoryEmbeddingStore<>();
+        //3， 构建EmbeddingStoreIngestor ，  完成文本数据的切割， 向量化， 存储
+        EmbeddingStoreIngestor ingestor = EmbeddingStoreIngestor.builder()
+                .embeddingStore(embeddingStore)
+                .build();
+        ingestor.ingest( documents);
+        return  embeddingStore;
+    }
+
+ //   @Bean("myEmbeddingStoreInMemory2")
+//    @Primary
+    public EmbeddingStore embeddingStoreInMemory2() throws IOException {
+        //1 , 加载知识库文档进 内存
+         List<Document> documents1 = ClassPathDocumentLoader.loadDocuments("knowledge\\pdf",new ApachePdfBoxDocumentParser());
+//        List<Document> documents2 = ClassPathDocumentLoader.loadDocuments("knowledge");
+
+        //2 ， 构建向量数据库操作对象
+        InMemoryEmbeddingStore<TextSegment> embeddingStore = new InMemoryEmbeddingStore<>();
+
+        //构建文档 分割器对象
+        DocumentSplitter recursiveSplitter = DocumentSplitters.recursive(300, 50);
+
+        //3， 构建EmbeddingStoreIngestor ，  完成文本数据的切割， 向量化， 存储
+        EmbeddingStoreIngestor ingestor = EmbeddingStoreIngestor.builder()
+                .embeddingStore(embeddingStore)
+                .documentSplitter(recursiveSplitter) //设置文档分割器
+//                .embeddingModel(embeddingModel)
+                .build();
+        ingestor.ingest( documents1);
+        return  embeddingStore;
+    }
+
+
+//    @Bean("myEmbeddingStoreInRedis")   不要打开，否则每次都会调用 阿里云的向量化模型 ，消耗token
+//    @Primary
+    public EmbeddingStore embeddingStoreInRedis() throws IOException {
+        //1 , 加载知识库文档进 内存
+        List<Document> documents1 = ClassPathDocumentLoader.loadDocuments("knowledge\\pdf",new ApachePdfBoxDocumentParser());
+//        List<Document> documents2 = ClassPathDocumentLoader.loadDocuments("knowledge");
+
+        //构建文档 分割器对象
+        DocumentSplitter recursiveSplitter = DocumentSplitters.recursive(300, 50);
+
+        //3， 构建EmbeddingStoreIngestor ，  完成文本数据的切割， 向量化， 存储
+        EmbeddingStoreIngestor ingestor = EmbeddingStoreIngestor.builder()
+                .embeddingStore(redisEmbeddingStore)
+                .documentSplitter(recursiveSplitter) //设置文档分割器
+                .embeddingModel(embeddingModel)
+                .build();
+        ingestor.ingest( documents1);
+        return  redisEmbeddingStore;
+    }
+
+    @Bean
+    public ContentRetriever contentRetriever(){
+        EmbeddingStoreContentRetriever contentRetriever = EmbeddingStoreContentRetriever.builder()
+                .embeddingStore(redisEmbeddingStore)
+                .embeddingModel(embeddingModel)
+                .minScore(0.5)//相似度
+                .maxResults(3) //最多返回3条
+                .build();
+        return  contentRetriever;
+    }
+
+
+
+}