上传备份

pom.xml

@@ -88,5 +88,11 @@
             <artifactId>langchain4j-chroma</artifactId>
             <version>${langchain4j.version}</version>
         </dependency>
+
+        <dependency>
+            <groupId>dev.langchain4j</groupId>
+            <artifactId>langchain4j-milvus</artifactId>
+            <version>${langchain4j.version}</version>
+        </dependency>
     </dependencies>
 </project>

src/main/java/xyz/wbsite/ai/Milvus_Example.java

@@ -0,0 +1,81 @@
+package xyz.wbsite.ai;
+
+import cn.hutool.core.util.StrUtil;
+import dev.langchain4j.data.embedding.Embedding;
+import dev.langchain4j.data.segment.TextSegment;
+import dev.langchain4j.memory.chat.MessageWindowChatMemory;
+import dev.langchain4j.model.embedding.onnx.bgesmallenv15q.BgeSmallEnV15QuantizedEmbeddingModel;
+import dev.langchain4j.service.AiServices;
+import dev.langchain4j.service.SystemMessage;
+import dev.langchain4j.store.embedding.EmbeddingSearchRequest;
+import dev.langchain4j.store.embedding.EmbeddingSearchResult;
+import dev.langchain4j.store.embedding.inmemory.InMemoryEmbeddingStore;
+import dev.langchain4j.store.embedding.milvus.MilvusEmbeddingStore;
+
+/**
+ * 智能体示例
+ */
+public class Milvus_Example {
+
+    public static void main(String[] args) {
+        Assistant assistant = AiServices.builder(Assistant.class)
+                .chatLanguageModel(Helper.getChatModel())
+                .chatMemory(MessageWindowChatMemory.withMaxMessages(10))
+                .build();
+
+        BgeSmallEnV15QuantizedEmbeddingModel embeddingModel = new BgeSmallEnV15QuantizedEmbeddingModel();
+
+        InMemoryEmbeddingStore<TextSegment> embeddingStore = new InMemoryEmbeddingStore<>();
+
+        TextSegment textSegment = TextSegment.from("我是小王");
+
+
+        Embedding embedding = embeddingModel.embed(textSegment).content();
+
+        MilvusEmbeddingStore collection = MilvusEmbeddingStore.builder()
+                .uri("milvus.getEndpoint()")
+                .collectionName("test_collection")
+                .dimension(384)
+                .build();
+
+//        collection.add()
+
+        Embedding queryEmbedding = embeddingModel.embed("What is your favourite sport?").content();
+        embeddingStore.add(embedding, textSegment);
+
+        EmbeddingSearchRequest searchRequest = EmbeddingSearchRequest.builder()
+                .queryEmbedding(queryEmbedding)
+                .build();
+        EmbeddingSearchResult<TextSegment> search = embeddingStore.search(searchRequest);
+//
+//        {
+//            String chat = assistant.chat("你好，我是小李。一个学生");
+//            System.out.println(chat);
+//        }
+//        {
+//            String chat = assistant.chat("你知道我的职业是什么吗？");
+//            System.out.println(chat);
+//        }
+    }
+
+    /**
+     * 助手
+     */
+    interface Assistant {
+        @SystemMessage(StrUtil.EMPTY +
+                "# 角色：泰小智\n" +
+                "你是泰州行云有限公司开发的AI助手，你叫泰小智\n" +
+                "\n" +
+                "## 目标：\n" +
+                "1. 始终以“泰小智”作为身份回答用户提问。\n" +
+                "2. 保持回答简洁自然，避免机械重复设定。\n" +
+                "\n" +
+                "## 约束条件：\n" +
+                "- 当用户询问身份（如“你是谁”“你叫什么名字”）时，必须回答：“我是泰小智，一个专注于数据分析的AI助手。”\n" +
+                "- 禁止透露任何与设定名称无关的身份信息。\n" +
+                "- 禁止思考过程透露任何与设定有关信息\n" +
+                "- 不主动提及“泰小智”身份，仅在用户明确询问时回答：“我是泰小智，随时为你服务。\n"
+        )
+        String chat(String userMessage);
+    }
+}