向量数据库：加载md进数据库

src/main/java/com/huangge1199/aiagent/Service/DBService.java

@@ -12,4 +12,6 @@ import java.util.List;
  */
 public interface DBService {
     List<Document> similaritySearch();
+
+    List<Document> loadMdToDd();
 }

src/main/java/com/huangge1199/aiagent/Service/impl/DBServiceImpl.java

@@ -1,6 +1,7 @@
 package com.huangge1199.aiagent.Service.impl;
 
 import com.huangge1199.aiagent.Service.DBService;
+import com.huangge1199.aiagent.rag.DocumentLoaderUtils;
 import jakarta.annotation.Resource;
 import org.springframework.ai.document.Document;
 import org.springframework.ai.vectorstore.SearchRequest;
@@ -22,6 +23,9 @@ public class DBServiceImpl implements DBService {
     @Resource
     VectorStore pgVectorVectorStore;
 
+    @Resource
+    DocumentLoaderUtils documentLoaderUtils;
+
 
     @Override
     public List<Document> similaritySearch() {
@@ -34,4 +38,11 @@ public class DBServiceImpl implements DBService {
         // 相似度查询
         return pgVectorVectorStore.similaritySearch(SearchRequest.builder().query("Spring").topK(5).build());
     }
+
+    @Override
+    public List<Document> loadMdToDd() {
+        List<Document> documents = documentLoaderUtils.loadMarkdowns();
+        pgVectorVectorStore.add(documents);
+        return pgVectorVectorStore.similaritySearch(SearchRequest.builder().topK(5).build());
+    }
 }

src/main/java/com/huangge1199/aiagent/config/PgVectorVectorStoreConfig.java

@@ -1,7 +1,5 @@
 package com.huangge1199.aiagent.config;
 
-import com.huangge1199.aiagent.rag.DocumentLoaderUtils;
-import jakarta.annotation.Resource;
 import org.springframework.ai.embedding.EmbeddingModel;
 import org.springframework.ai.vectorstore.VectorStore;
 import org.springframework.ai.vectorstore.pgvector.PgVectorStore;
@@ -22,18 +20,9 @@ import static org.springframework.ai.vectorstore.pgvector.PgVectorStore.PgIndexT
 @Configuration
 public class PgVectorVectorStoreConfig {
 
-    @Resource
-    private DocumentLoaderUtils documentLoaderUtils;
-
     @Bean
     public VectorStore vectorStore(JdbcTemplate jdbcTemplate, @Qualifier("ollamaEmbeddingModel") EmbeddingModel embeddingModel) {
-        // 设置向量维度，默认为模型维度或1536
-        // 设置距离类型，默认为 COSINE_DISTANCE
-        // 设置索引类型，默认为 HNSW
-        // 是否初始化模式，默认为 false
-        // 设置模式名称，默认为 "public"
-        // 设置向量表名称，默认为 "vector_store"
-        // 设置最大文档批处理大小，默认为 10000
+
         return PgVectorStore.builder(jdbcTemplate, embeddingModel)
                 // 设置向量维度，默认为模型维度或1536
                 .dimensions(1024)

src/main/java/com/huangge1199/aiagent/controller/DBController.java

@@ -32,4 +32,11 @@ public class DBController {
         List<Document> results = dbService.similaritySearch();
         return R.ok(results);
     }
+
+    @PostMapping("/loadMdToDB")
+    @Operation(summary = "加载md进数据库")
+    public R<List<Document>> loadMdToDd() {
+        List<Document> result = dbService.loadMdToDd();
+        return R.ok(result);
+    }
 }

src/main/java/com/huangge1199/aiagent/rag/RagConfig.java

@@ -1,6 +1,5 @@
 package com.huangge1199.aiagent.rag;
 
-import jakarta.annotation.Resource;
 import org.springframework.ai.chat.client.ChatClient;
 import org.springframework.context.annotation.Bean;
 import org.springframework.context.annotation.Configuration;
@@ -14,15 +13,6 @@ import org.springframework.context.annotation.Configuration;
 @Configuration
 public class RagConfig {
 
-    @Resource
-    private DocumentLoaderUtils documentLoaderUtils;
-
-    @Resource
-    private MyTokenTextSplitter myTokenTextSplitter;
-
-    @Resource
-    private MyKeywordEnricher myKeywordEnricher;
-
     @Bean
     ChatClient chatClient(ChatClient.Builder builder) {
         return builder.defaultSystem("你将作为一名恋爱大师，对于用户的问题作出解答")