diff --git a/src/main/java/xyz/wbsite/ai/Agent_Example.java b/src/main/java/xyz/wbsite/ai/Agent_Example.java
new file mode 100644
index 0000000..037dda0
--- /dev/null
+++ b/src/main/java/xyz/wbsite/ai/Agent_Example.java
@@ -0,0 +1,48 @@
+package xyz.wbsite.ai;
+
+import cn.hutool.core.collection.CollUtil;
+import cn.hutool.core.util.StrUtil;
+import dev.langchain4j.data.message.ChatMessage;
+import dev.langchain4j.data.message.UserMessage;
+import dev.langchain4j.memory.chat.MessageWindowChatMemory;
+import dev.langchain4j.service.AiServices;
+import dev.langchain4j.service.SystemMessage;
+
+import java.util.List;
+
+/**
+ * 智能体示例
+ */
+public class Agent_Example {
+
+    public static void main(String[] args) {
+        Assistant assistant = AiServices.builder(Assistant.class)
+                .chatLanguageModel(Helper.getChatModel())
+                .chatMemory(MessageWindowChatMemory.withMaxMessages(10))
+                .build();
+
+        String chat = assistant.chat("你是谁");
+        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);
+    }
+}
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/Base_Chat_Example.java b/src/main/java/xyz/wbsite/ai/Base_Chat_Example.java
new file mode 100644
index 0000000..dcd90fb
--- /dev/null
+++ b/src/main/java/xyz/wbsite/ai/Base_Chat_Example.java
@@ -0,0 +1,12 @@
+package xyz.wbsite.ai;
+
+/**
+ * 最简单的聊天示例
+ */
+public class Base_Chat_Example {
+
+    public static void main(String[] args) {
+        String chat = Helper.getChatModel().chat("你是谁");
+        System.out.println(chat);
+    }
+}
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/Base_StreamChat_Example.java b/src/main/java/xyz/wbsite/ai/Base_StreamChat_Example.java
new file mode 100644
index 0000000..ef67b34
--- /dev/null
+++ b/src/main/java/xyz/wbsite/ai/Base_StreamChat_Example.java
@@ -0,0 +1,38 @@
+package xyz.wbsite.ai;
+
+import cn.hutool.core.thread.ThreadUtil;
+import dev.langchain4j.model.chat.response.ChatResponse;
+import dev.langchain4j.model.chat.response.StreamingChatResponseHandler;
+
+/**
+ * 简单的流式聊天示例
+ */
+public class Base_StreamChat_Example {
+
+    public static void main(String[] args) {
+
+        String question = "假如树上有10只鸟，10分钟前飞走了2只，5分钟前又飞回了1只，刚刚又来了3只，那现在树上有几只鸟?";
+
+        ThreadUtil.execAsync(new Runnable() {
+            @Override
+            public void run() {
+                Helper.getStreamChatModel().chat(question, new StreamingChatResponseHandler() {
+                    @Override
+                    public void onPartialResponse(String s) {
+                        System.out.print(s);
+                    }
+
+                    @Override
+                    public void onCompleteResponse(ChatResponse chatResponse) {
+                        System.out.println("onComplete");
+                    }
+
+                    @Override
+                    public void onError(Throwable throwable) {
+                        System.err.println(throwable.getMessage());
+                    }
+                });
+            }
+        });
+    }
+}
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/TestToolChat.java b/src/main/java/xyz/wbsite/ai/Base_Tool_Example.java
similarity index 58%
rename from src/main/java/xyz/wbsite/ai/TestToolChat.java
rename to src/main/java/xyz/wbsite/ai/Base_Tool_Example.java
index 86b816d..76c3259 100644
--- a/src/main/java/xyz/wbsite/ai/TestToolChat.java
+++ b/src/main/java/xyz/wbsite/ai/Base_Tool_Example.java
@@ -1,7 +1,10 @@
 package xyz.wbsite.ai;
 
-import dev.langchain4j.agent.tool.*;
-import dev.langchain4j.chain.ConversationalChain;
+import dev.langchain4j.agent.tool.P;
+import dev.langchain4j.agent.tool.Tool;
+import dev.langchain4j.agent.tool.ToolExecutionRequest;
+import dev.langchain4j.agent.tool.ToolSpecification;
+import dev.langchain4j.agent.tool.ToolSpecifications;
 import dev.langchain4j.data.message.AiMessage;
 import dev.langchain4j.data.message.ChatMessage;
 import dev.langchain4j.data.message.ToolExecutionResultMessage;
@@ -9,9 +12,6 @@ import dev.langchain4j.data.message.UserMessage;
 import dev.langchain4j.model.chat.request.ChatRequest;
 import dev.langchain4j.model.chat.request.ChatRequestParameters;
 import dev.langchain4j.model.chat.response.ChatResponse;
-import dev.langchain4j.model.openai.OpenAiChatModel;
-import dev.langchain4j.model.openai.OpenAiStreamingChatModel;
-import dev.langchain4j.service.TokenStream;
 import dev.langchain4j.service.tool.DefaultToolExecutor;
 import dev.langchain4j.service.tool.ToolExecutor;
 
@@ -21,17 +21,11 @@ import java.util.UUID;
 import java.util.function.Consumer;
 
 /**
- * 主函数入口
+ * Tool调用基本用法，需要自行实现AI回调消息
  */
-public class TestToolChat {
+public class Base_Tool_Example {
 
     public static void main(String[] args) {
-        OpenAiChatModel model = OpenAiChatModel.builder()
-                .baseUrl("http://36.138.207.178:11434/v1")
-                .apiKey("1")
-                .modelName("deepseek-r1:14B")
-                .build();
-
         List<ChatMessage> chatMessages = new ArrayList<>();
         chatMessages.add(UserMessage.from("请问，泰州市的天气怎么样？"));
 
@@ -53,7 +47,7 @@ public class TestToolChat {
                 .build();
 
 
-        ChatResponse chatResponse = model.chat(chatRequest);
+        ChatResponse chatResponse = Helper.getToolChatModel().chat(chatRequest);
         AiMessage aiMessage = chatResponse.aiMessage();
         chatMessages.add(aiMessage);
         if (aiMessage.hasToolExecutionRequests()) {
@@ -64,7 +58,6 @@ public class TestToolChat {
                 @Override
                 public void accept(ToolExecutionRequest toolExecutionRequest) {
                     ToolExecutor toolExecutor = new DefaultToolExecutor(weatherTools, toolExecutionRequest);
-                    System.out.println("Now let's execute the tool " + toolExecutionRequest.name());
                     String result = toolExecutor.execute(toolExecutionRequest, UUID.randomUUID().toString());
                     ToolExecutionResultMessage toolExecutionResultMessages = ToolExecutionResultMessage.from(toolExecutionRequest, result);
                     chatMessages.add(toolExecutionResultMessages);
@@ -72,54 +65,13 @@ public class TestToolChat {
             });
         }
 
-        // STEP 4: Model generates final response
         ChatRequest chatRequest2 = ChatRequest.builder()
                 .messages(chatMessages)
                 .parameters(ChatRequestParameters.builder()
                         .toolSpecifications(toolSpecifications)
                         .build())
                 .build();
-        ChatResponse finalChatResponse = model.chat(chatRequest2);
+        ChatResponse finalChatResponse = Helper.getToolChatModel().chat(chatRequest2);
         System.out.println(finalChatResponse.aiMessage().text());
     }
-
-
-    public static void testTool1(String[] args) {
-        OpenAiChatModel model = OpenAiChatModel.builder()
-                .baseUrl("http://36.138.207.178:11434/v1")
-                .apiKey("1")
-                .modelName("qwen2.5:7b")
-                .build();
-
-        List<ChatMessage> chatMessages = new ArrayList<>();
-        chatMessages.add(UserMessage.from("请问，泰州市的天气怎么样？"));
-
-        Object weatherTools = new Object() {
-            @Tool("返回某一城市的天气情况")
-            public String getWeather(@P("应返回天气预报的城市") String city) {
-                System.out.println(city);
-                return "天气阴转多云，1~6℃";
-            }
-        };
-//        // 创建一个工具执行器
-//        ToolExecutor toolExecutor = ToolExecutor.builder()
-//                .tool(weatherTools)
-//                .build();
-
-        ConversationalChain.builder()
-                .chatLanguageModel(model)
-                .build();
-    }
-
-    // 创建一个助手接口
-    interface Assistant {
-
-        String chat(String userMessage);
-
-        TokenStream chatStream(List<ChatMessage> messages);
-
-        TokenStream chatStream(ChatMessage message);
-
-        TokenStream chatStream(String message);
-    }
 }
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/Easy_RAG_Example.java b/src/main/java/xyz/wbsite/ai/Easy_RAG_Example.java
new file mode 100644
index 0000000..4e9b4b0
--- /dev/null
+++ b/src/main/java/xyz/wbsite/ai/Easy_RAG_Example.java
@@ -0,0 +1,50 @@
+package xyz.wbsite.ai;
+
+import dev.langchain4j.data.document.Document;
+import dev.langchain4j.data.segment.TextSegment;
+import dev.langchain4j.memory.chat.MessageWindowChatMemory;
+import dev.langchain4j.rag.content.retriever.EmbeddingStoreContentRetriever;
+import dev.langchain4j.service.AiServices;
+import dev.langchain4j.service.SystemMessage;
+import dev.langchain4j.store.embedding.EmbeddingStoreIngestor;
+import dev.langchain4j.store.embedding.inmemory.InMemoryEmbeddingStore;
+
+import java.util.List;
+
+/**
+ * Easy-RAG 示例
+ */
+public class Easy_RAG_Example {
+
+    public static void main(String[] args) {
+        // 加载文档
+        List<Document> documents = Helper.getDocuments();
+
+        // 创建一个内存存储器，用于存储文档和其嵌入
+        InMemoryEmbeddingStore<TextSegment> embeddingStore = new InMemoryEmbeddingStore<>();
+
+        // 使用easy-rag，可以最快捷的方式使用rag
+        EmbeddingStoreIngestor.ingest(documents, embeddingStore);
+
+        Assistant assistant = AiServices.builder(Assistant.class)
+                .chatLanguageModel(Helper.getChatModel())
+                .chatMemory(MessageWindowChatMemory.withMaxMessages(10))
+                .contentRetriever(EmbeddingStoreContentRetriever.from(embeddingStore))
+                .build();
+
+        String chat = assistant.chat("小猪在睡觉的时候会干嘛？");
+        System.out.println(chat);
+
+        String chat1 = assistant.chat("刺猬睡觉的时候会干嘛？");
+        System.out.println(chat1);
+    }
+
+    /**
+     * 助手
+     */
+    interface Assistant {
+
+        @SystemMessage("请参考提供资料，不要发散，没有请直接回答查到")
+        String chat(String userMessage);
+    }
+}
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/Easy_StreamChat_Example.java b/src/main/java/xyz/wbsite/ai/Easy_StreamChat_Example.java
new file mode 100644
index 0000000..2b0238d
--- /dev/null
+++ b/src/main/java/xyz/wbsite/ai/Easy_StreamChat_Example.java
@@ -0,0 +1,42 @@
+package xyz.wbsite.ai;
+
+import cn.hutool.core.thread.ThreadUtil;
+import dev.langchain4j.memory.chat.MessageWindowChatMemory;
+import dev.langchain4j.service.AiServices;
+import dev.langchain4j.service.TokenStream;
+
+/**
+ * 简单的流式聊天示例
+ */
+public class Easy_StreamChat_Example {
+
+    public static void main(String[] args) {
+
+        String question = "你是谁?";
+
+        Assistant assistant = AiServices.builder(Assistant.class)
+                .streamingChatLanguageModel(Helper.getStreamChatModel())
+                .chatMemory(MessageWindowChatMemory.withMaxMessages(10))
+                .build();
+
+        assistant.chat(question)
+                .onPartialResponse(System.out::print)
+                .onCompleteResponse(chatResponse -> {
+                    System.out.println();
+                    System.out.println("onComplete");
+                })
+                .ignoreErrors()
+                .start();
+
+        ThreadUtil.sleep(10 * 1000);
+    }
+
+
+    /**
+     * 助手
+     */
+    interface Assistant {
+
+        TokenStream chat(String userMessage);
+    }
+}
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/TestTool2Chat.java b/src/main/java/xyz/wbsite/ai/Easy_Tool_Example.java
similarity index 58%
rename from src/main/java/xyz/wbsite/ai/TestTool2Chat.java
rename to src/main/java/xyz/wbsite/ai/Easy_Tool_Example.java
index d3144b0..5ededf8 100644
--- a/src/main/java/xyz/wbsite/ai/TestTool2Chat.java
+++ b/src/main/java/xyz/wbsite/ai/Easy_Tool_Example.java
@@ -2,26 +2,17 @@ package xyz.wbsite.ai;
 
 import dev.langchain4j.agent.tool.P;
 import dev.langchain4j.agent.tool.Tool;
-import dev.langchain4j.data.message.ChatMessage;
 import dev.langchain4j.memory.chat.MessageWindowChatMemory;
-import dev.langchain4j.model.openai.OpenAiChatModel;
 import dev.langchain4j.service.AiServices;
-import dev.langchain4j.service.TokenStream;
-
-import java.util.List;
 
 /**
- * 主函数入口
+ * 简易工具调用示例
  */
-public class TestTool2Chat {
+public class Easy_Tool_Example {
 
     public static void main(String[] args) {
-        OpenAiChatModel model = OpenAiChatModel.builder()
-                .baseUrl("http://36.138.207.178:11434/v1")
-                .apiKey("1")
-                .modelName("qwen2.5:7b")
-                .build();
 
+        // 工具类
         Object weatherTools = new Object() {
             @Tool("返回某一城市的天气情况")
             public String getWeather(@P("应返回天气预报的城市") String city) {
@@ -31,8 +22,8 @@ public class TestTool2Chat {
         };
 
         Assistant agent = AiServices.builder(Assistant.class)
-                .chatLanguageModel(model)
-                .tools(weatherTools)
+                .chatLanguageModel(Helper.getToolChatModel()) // 设置工具聊天模型
+                .tools(weatherTools) // 设置工具
                 .chatMemory(MessageWindowChatMemory.withMaxMessages(10))
                 .build();
 
@@ -40,16 +31,9 @@ public class TestTool2Chat {
         System.out.println(chat);
     }
 
-
     // 创建一个助手接口
     interface Assistant {
 
         String chat(String userMessage);
-
-        TokenStream chatStream(List<ChatMessage> messages);
-
-        TokenStream chatStream(ChatMessage message);
-
-        TokenStream chatStream(String message);
     }
 }
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/Helper.java b/src/main/java/xyz/wbsite/ai/Helper.java
new file mode 100644
index 0000000..4c8a75a
--- /dev/null
+++ b/src/main/java/xyz/wbsite/ai/Helper.java
@@ -0,0 +1,63 @@
+package xyz.wbsite.ai;
+
+import cn.hutool.core.collection.CollUtil;
+import dev.langchain4j.data.document.Document;
+import dev.langchain4j.model.openai.OpenAiChatModel;
+import dev.langchain4j.model.openai.OpenAiStreamingChatModel;
+
+import java.util.List;
+
+public class Helper {
+
+    private static OpenAiStreamingChatModel openAiStreamingChatModel = OpenAiStreamingChatModel.builder()
+            .baseUrl("http://36.138.207.178:11434/v1")
+            .apiKey("1")
+            .modelName("deepseek-r1:14B")
+            .logRequests(true)
+            .logResponses(true)
+            .build();
+
+    private static  OpenAiChatModel openAiChatModel = OpenAiChatModel.builder()
+            .baseUrl("http://36.138.207.178:11434/v1")
+            .apiKey("1")
+            .modelName("deepseek-r1:14B")
+            .logRequests(true)
+            .logResponses(true)
+            .build();
+
+    private static  OpenAiChatModel toolChatModel = OpenAiChatModel.builder()
+            .baseUrl("http://36.138.207.178:11434/v1")
+            .apiKey("1")
+            .modelName("qwen2.5:7b")
+            .build();
+
+    public static OpenAiStreamingChatModel getStreamChatModel() {
+        return openAiStreamingChatModel;
+    }
+
+    public static OpenAiChatModel getChatModel() {
+        return openAiChatModel;
+    }
+
+    public static OpenAiChatModel getToolChatModel() {
+        return toolChatModel;
+    }
+
+    public static Document getDocument() {
+        return Document.from("人往往在做梦的时候会打呼噜");
+    }
+
+    public static Document getDocument(String text) {
+        return Document.from(text);
+    }
+
+    public static List<Document> getDocuments() {
+        return CollUtil.newArrayList(
+                Document.from("人往往在做梦的时候会打呼噜"),
+                Document.from("小猪在睡觉的时候会扭屁股"),
+                Document.from("有一只蟑螂在床底下跳舞"),
+                Document.from("小狗在睡觉的时候会磨牙"),
+                Document.from("我家的小鸡喜欢吃虫子")
+        );
+    }
+}
diff --git a/src/main/java/xyz/wbsite/ai/Naive_RAG_Example.java b/src/main/java/xyz/wbsite/ai/Naive_RAG_Example.java
new file mode 100644
index 0000000..8e5fe3f
--- /dev/null
+++ b/src/main/java/xyz/wbsite/ai/Naive_RAG_Example.java
@@ -0,0 +1,91 @@
+package xyz.wbsite.ai;
+
+import dev.langchain4j.data.document.Document;
+import dev.langchain4j.data.document.DocumentSplitter;
+import dev.langchain4j.data.document.splitter.DocumentSplitters;
+import dev.langchain4j.data.embedding.Embedding;
+import dev.langchain4j.data.segment.TextSegment;
+import dev.langchain4j.memory.ChatMemory;
+import dev.langchain4j.memory.chat.MessageWindowChatMemory;
+import dev.langchain4j.model.embedding.EmbeddingModel;
+import dev.langchain4j.model.embedding.onnx.bgesmallenv15q.BgeSmallEnV15QuantizedEmbeddingModel;
+import dev.langchain4j.rag.content.retriever.ContentRetriever;
+import dev.langchain4j.rag.content.retriever.EmbeddingStoreContentRetriever;
+import dev.langchain4j.service.AiServices;
+import dev.langchain4j.store.embedding.EmbeddingStore;
+import dev.langchain4j.store.embedding.inmemory.InMemoryEmbeddingStore;
+
+import java.util.List;
+
+/**
+ * 主函数入口
+ */
+public class Naive_RAG_Example {
+
+    public static void main(String[] args) {
+        // 加载文档
+        Document document = Helper.getDocument();
+
+        //现在，我们需要将此文档拆分为更小的部分，也称为“块”
+        //这种方法允许我们仅向LLM发送相关段以响应用户查询，
+        //而不是整个文档。例如如果用户询问取消政策，
+        //我们将仅识别并发送与取消相关的片段。
+        //一个好的起点是使用递归文档拆分器，最初尝试
+        //按段落分割。如果一个段落太大而无法放入单个片段中，
+        //拆分器将递归地按换行符、句子和单词进行划分，
+        //如有必要，确保每段文本都适合一个片段。
+        DocumentSplitter splitter = DocumentSplitters.recursive(300, 0);
+        List<TextSegment> segments = splitter.split(document);
+
+        //现在，我们需要嵌入（也称为“矢量化”）这些片段。
+        //执行相似性搜索需要嵌入。
+        //对于这个例子，我们将使用本地进程内嵌入模型，但您可以选择任何支持的模型。
+        //Langchain4j目前支持10多个流行的嵌入模型提供者。
+        EmbeddingModel embeddingModel = new BgeSmallEnV15QuantizedEmbeddingModel();
+        List<Embedding> embeddings = embeddingModel.embedAll(segments).content();
+
+        //接下来，我们将把这些嵌入存储在嵌入存储中（也称为“向量数据库”）。
+        //此存储将用于在每次与LLM交互时搜索相关细分市场。
+        //为简单起见，此示例使用内存中的嵌入存储，但您可以从任何支持的存储中进行选择。
+        //Langchain4j目前支持超过15个流行的嵌入商店。
+        EmbeddingStore<TextSegment> embeddingStore = new InMemoryEmbeddingStore<>();
+        embeddingStore.addAll(embeddings, segments);
+
+        // 我们还可以使用EmbeddingStoreIngestor将上面的手动步骤隐藏在更简单的API后面。
+        // 请参阅_01_Advanced_RAG_with_Query_Compression_example中使用嵌入式存储器的示例。
+
+        //内容检索器负责根据用户查询检索相关内容。
+        //目前，它能够检索文本段，但未来的增强功能将包括支持
+        //其他模态，如图像、音频等。
+        ContentRetriever contentRetriever = EmbeddingStoreContentRetriever.builder()
+                .embeddingStore(embeddingStore)
+                .embeddingModel(embeddingModel)
+                .maxResults(2) // 在每次交互中，我们将检索2个最相关的片段
+                .minScore(0.1) // 我们希望检索至少与用户查询有些相似的段
+                .build();
+
+        //我们可以选择使用聊天存储器，与LLM进行来回对话
+        //并允许它记住之前的交互。
+        //目前，LangChain4j提供了两种聊天内存实现：
+        //MessageWindowChatMemory和TokenWindowChatMemory。
+        ChatMemory chatMemory = MessageWindowChatMemory.withMaxMessages(10);
+
+        //最后一步是构建我们的人工智能服务，
+        //配置它以使用我们上面创建的组件。
+        Assistant assistant = AiServices.builder(Assistant.class)
+                .chatLanguageModel(Helper.getChatModel())
+                .contentRetriever(contentRetriever)
+                .chatMemory(chatMemory)
+                .build();
+
+        String chat = assistant.chat("你是谁？");
+        System.out.println(chat);
+    }
+
+
+    // 创建一个助手接口
+    interface Assistant {
+
+        String chat(String userMessage);
+    }
+}
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/Query_Compression_Example.java b/src/main/java/xyz/wbsite/ai/Query_Compression_Example.java
new file mode 100644
index 0000000..eef8faa
--- /dev/null
+++ b/src/main/java/xyz/wbsite/ai/Query_Compression_Example.java
@@ -0,0 +1,75 @@
+package xyz.wbsite.ai;
+
+import dev.langchain4j.data.document.splitter.DocumentSplitters;
+import dev.langchain4j.data.segment.TextSegment;
+import dev.langchain4j.memory.chat.MessageWindowChatMemory;
+import dev.langchain4j.model.embedding.EmbeddingModel;
+import dev.langchain4j.model.embedding.onnx.bgesmallenv15q.BgeSmallEnV15QuantizedEmbeddingModel;
+import dev.langchain4j.rag.DefaultRetrievalAugmentor;
+import dev.langchain4j.rag.content.retriever.EmbeddingStoreContentRetriever;
+import dev.langchain4j.rag.query.transformer.CompressingQueryTransformer;
+import dev.langchain4j.service.AiServices;
+import dev.langchain4j.store.embedding.EmbeddingStoreIngestor;
+import dev.langchain4j.store.embedding.inmemory.InMemoryEmbeddingStore;
+
+/**
+ * 对上下文对话进行查询压缩
+ */
+public class Query_Compression_Example {
+
+    public static void main(String[] args) {
+
+        EmbeddingModel embeddingModel = new BgeSmallEnV15QuantizedEmbeddingModel();
+
+        InMemoryEmbeddingStore<TextSegment> embeddingStore = new InMemoryEmbeddingStore<>();
+
+        EmbeddingStoreIngestor ingestor = EmbeddingStoreIngestor.builder()
+                .documentSplitter(DocumentSplitters.recursive(300, 0))
+                .embeddingStore(embeddingStore)
+                .embeddingModel(embeddingModel)
+                .build();
+
+        ingestor.ingest(Helper.getDocument());
+
+        EmbeddingStoreContentRetriever retriever = EmbeddingStoreContentRetriever.builder()
+                .embeddingModel(embeddingModel)
+                .embeddingStore(embeddingStore)
+                .maxResults(2)
+                .minScore(0.5)
+                .build();
+
+        CompressingQueryTransformer queryTransformer = new CompressingQueryTransformer(Helper.getChatModel());
+//        // 其他实现
+//        QueryTransformer queryTransformer = new QueryTransformer() {
+//            @Override
+//            public Collection<Query> transform(Query query) {
+//                return CollUtil.newArrayList(new Query(query.text().toLowerCase()));
+//            }
+//        };
+
+        DefaultRetrievalAugmentor retrievalAugmentor = DefaultRetrievalAugmentor.builder()
+                .queryTransformer(queryTransformer)
+                .contentRetriever(retriever)
+                .build();
+
+        Assistant assistant = AiServices.builder(Assistant.class)
+                .chatLanguageModel(Helper.getChatModel())
+                .retrievalAugmentor(retrievalAugmentor)
+                .chatMemory(MessageWindowChatMemory.withMaxMessages(4))
+                .build();
+
+        String chat = assistant.chat("人在睡觉时会做什么了？");
+        System.out.println(chat);
+
+        String chat1 = assistant.chat("小猪在睡觉的时候会什么了？");
+        System.out.println(chat1);
+    }
+
+    /**
+     * 助手
+     */
+    interface Assistant {
+
+        String chat(String userMessage);
+    }
+}
diff --git a/src/main/java/xyz/wbsite/ai/TestRagChat.java b/src/main/java/xyz/wbsite/ai/TestRagChat.java
deleted file mode 100644
index 12d2b4c..0000000
--- a/src/main/java/xyz/wbsite/ai/TestRagChat.java
+++ /dev/null
@@ -1,97 +0,0 @@
-package xyz.wbsite.ai;
-
-import cn.hutool.core.collection.CollUtil;
-import dev.langchain4j.agent.tool.*;
-import dev.langchain4j.chain.ConversationalChain;
-import dev.langchain4j.data.document.Document;
-import dev.langchain4j.data.message.*;
-import dev.langchain4j.data.segment.TextSegment;
-import dev.langchain4j.memory.chat.MessageWindowChatMemory;
-import dev.langchain4j.model.chat.request.ChatRequest;
-import dev.langchain4j.model.chat.response.ChatResponse;
-import dev.langchain4j.model.openai.OpenAiChatModel;
-import dev.langchain4j.model.openai.OpenAiStreamingChatModel;
-import dev.langchain4j.rag.content.retriever.EmbeddingStoreContentRetriever;
-import dev.langchain4j.service.AiServices;
-import dev.langchain4j.service.TokenStream;
-import dev.langchain4j.service.tool.DefaultToolExecutor;
-import dev.langchain4j.service.tool.ToolExecutor;
-import dev.langchain4j.store.embedding.EmbeddingStoreIngestor;
-import dev.langchain4j.store.embedding.inmemory.InMemoryEmbeddingStore;
-
-import java.util.ArrayList;
-import java.util.List;
-import java.util.UUID;
-import java.util.function.Consumer;
-
-/**
- * 主函数入口
- */
-public class TestRagChat {
-
-    public static void main(String[] args) {
-        OpenAiStreamingChatModel model = OpenAiStreamingChatModel.builder()
-                .baseUrl("http://36.138.207.178:11434/v1")
-                .apiKey("1")
-                .modelName("deepseek-r1:14B")
-                .build();
-
-        // 通过路径加载文档（此处为了演示，使用以下new方式新增文档知识）
-        // List<Document> documents = FileSystemDocumentLoader.loadDocuments("path");
-        List<Document> documents = CollUtil.newArrayList(
-                Document.from("人往往在做梦的时候会打呼噜"),
-                Document.from("小猪在睡觉的时候会扭屁股"),
-                Document.from("有一只蟑螂在床底下跳舞"),
-                Document.from("小狗在睡觉的时候会磨牙"),
-                Document.from("我家的小鸡喜欢吃虫子")
-        );
-
-        // 创建一个内存存储器，用于存储文档和其嵌入
-        InMemoryEmbeddingStore<TextSegment> embeddingStore = new InMemoryEmbeddingStore<>();
-
-        // 使用easy-rag，可以最快捷的方式使用rag
-        EmbeddingStoreIngestor.ingest(documents, embeddingStore);
-
-        Assistant assistant = AiServices.builder(Assistant.class)
-                .streamingChatLanguageModel(model)
-                .chatMemory(MessageWindowChatMemory.withMaxMessages(10))
-                .contentRetriever(EmbeddingStoreContentRetriever.from(embeddingStore))
-                .build();
-
-        List<ChatMessage> messages = CollUtil.newArrayList(
-                SystemMessage.from("" +
-                        "# 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：“我是豆包，随时为你服务。\n"),
-                UserMessage.from("你是谁")
-        );
-
-        assistant.chatStream(messages)
-                .onPartialResponse(System.out::print)
-                .onError(throwable -> System.err.println("Error: " + throwable.getMessage()))
-                .onCompleteResponse(chatResponse -> System.out.println("Complete Response: "))
-                .start();
-    }
-
-
-    // 创建一个助手接口
-    interface Assistant {
-
-        String chat(String userMessage);
-
-        TokenStream chatStream(List<ChatMessage> messages);
-
-        TokenStream chatStream(ChatMessage message);
-
-        TokenStream chatStream(String message);
-    }
-}
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/TestRagNativeChat.java b/src/main/java/xyz/wbsite/ai/TestRagNativeChat.java
deleted file mode 100644
index 2199376..0000000
--- a/src/main/java/xyz/wbsite/ai/TestRagNativeChat.java
+++ /dev/null
@@ -1,122 +0,0 @@
-package xyz.wbsite.ai;
-
-import dev.langchain4j.data.document.Document;
-import dev.langchain4j.data.document.DocumentParser;
-import dev.langchain4j.data.document.DocumentSplitter;
-import dev.langchain4j.data.document.loader.FileSystemDocumentLoader;
-import dev.langchain4j.data.document.parser.TextDocumentParser;
-import dev.langchain4j.data.document.splitter.DocumentSplitters;
-import dev.langchain4j.data.embedding.Embedding;
-import dev.langchain4j.data.message.ChatMessage;
-import dev.langchain4j.data.segment.TextSegment;
-import dev.langchain4j.memory.chat.MessageWindowChatMemory;
-import dev.langchain4j.model.embedding.EmbeddingModel;
-import dev.langchain4j.model.embedding.onnx.bgesmallenv15q.BgeSmallEnV15QuantizedEmbeddingModel;
-import dev.langchain4j.model.openai.OpenAiChatModel;
-import dev.langchain4j.model.openai.OpenAiStreamingChatModel;
-import dev.langchain4j.rag.content.Content;
-import dev.langchain4j.rag.content.retriever.ContentRetriever;
-import dev.langchain4j.rag.content.retriever.EmbeddingStoreContentRetriever;
-import dev.langchain4j.rag.query.Query;
-import dev.langchain4j.service.AiServices;
-import dev.langchain4j.service.TokenStream;
-import dev.langchain4j.store.embedding.EmbeddingStore;
-import dev.langchain4j.store.embedding.inmemory.InMemoryEmbeddingStore;
-
-import java.util.List;
-
-import static dev.langchain4j.data.document.loader.FileSystemDocumentLoader.loadDocument;
-
-/**
- * 主函数入口
- */
-public class TestRagNativeChat {
-
-    public static void main(String[] args) {
-        OpenAiChatModel model = OpenAiChatModel.builder()
-                .baseUrl("http://36.138.207.178:11434/v1")
-                .apiKey("1")
-                .modelName("deepseek-r1:14B")
-                .build();
-
-
-
-        // Now, let's load a document that we want to use for RAG.
-        // We will use the terms of use from an imaginary car rental company, "Miles of Smiles".
-        // For this example, we'll import only a single document, but you can load as many as you need.
-        // LangChain4j offers built-in support for loading documents from various sources:
-        // File System, URL, Amazon S3, Azure Blob Storage, GitHub, Tencent COS.
-        // Additionally, LangChain4j supports parsing multiple document types:
-        // text, pdf, doc, xls, ppt.
-        // However, you can also manually import your data from other sources.
-        DocumentParser documentParser = new TextDocumentParser();
-        Document document = loadDocument("D:\\docs\\人才公共服务平台会议纪要20210720.txt", documentParser);
-
-
-        // Now, we need to split this document into smaller segments, also known as "chunks."
-        // This approach allows us to send only relevant segments to the LLM in response to a user query,
-        // rather than the entire document. For instance, if a user asks about cancellation policies,
-        // we will identify and send only those segments related to cancellation.
-        // A good starting point is to use a recursive document splitter that initially attempts
-        // to split by paragraphs. If a paragraph is too large to fit into a single segment,
-        // the splitter will recursively divide it by newlines, then by sentences, and finally by words,
-        // if necessary, to ensure each piece of text fits into a single segment.
-        DocumentSplitter splitter = DocumentSplitters.recursive(300, 0);
-        List<TextSegment> segments = splitter.split(document);
-
-
-        // Now, we need to embed (also known as "vectorize") these segments.
-        // Embedding is needed for performing similarity searches.
-        // For this example, we'll use a local in-process embedding model, but you can choose any supported model.
-        // Langchain4j currently supports more than 10 popular embedding model providers.
-        EmbeddingModel embeddingModel = new BgeSmallEnV15QuantizedEmbeddingModel();
-        List<Embedding> embeddings = embeddingModel.embedAll(segments).content();
-
-
-        // Next, we will store these embeddings in an embedding store (also known as a "vector database").
-        // This store will be used to search for relevant segments during each interaction with the LLM.
-        // For simplicity, this example uses an in-memory embedding store, but you can choose from any supported store.
-        // Langchain4j currently supports more than 15 popular embedding stores.
-        EmbeddingStore<TextSegment> embeddingStore = new InMemoryEmbeddingStore<>();
-        embeddingStore.addAll(embeddings, segments);
-
-        // We could also use EmbeddingStoreIngestor to hide manual steps above behind a simpler API.
-        // See an example of using EmbeddingStoreIngestor in _01_Advanced_RAG_with_Query_Compression_Example.
-
-
-        // The content retriever is responsible for retrieving relevant content based on a user query.
-        // Currently, it is capable of retrieving text segments, but future enhancements will include support for
-        // additional modalities like images, audio, and more.
-        ContentRetriever contentRetriever = EmbeddingStoreContentRetriever.builder()
-                .embeddingStore(embeddingStore)
-                .embeddingModel(embeddingModel)
-                .maxResults(2) // on each interaction we will retrieve the 2 most relevant segments
-                .minScore(0.1) // we want to retrieve segments at least somewhat similar to user query
-                .build();
-
-        List<Content> retrieve = contentRetriever.retrieve(new Query("参会人员有哪些人？"));
-        System.out.println();
-
-        Assistant assistant = AiServices.builder(Assistant.class)
-                .chatLanguageModel(model)
-                .chatMemory(MessageWindowChatMemory.withMaxMessages(10))
-                .contentRetriever(contentRetriever)
-                .build();
-
-        // String chat = assistant.chat("参会人员有哪些人？");
-        //System.out.println(chat);
-    }
-
-
-    // 创建一个助手接口
-    interface Assistant {
-
-        String chat(String userMessage);
-
-        TokenStream chatStream(List<ChatMessage> messages);
-
-        TokenStream chatStream(ChatMessage message);
-
-        TokenStream chatStream(String message);
-    }
-}
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/TestSimpleChat.java b/src/main/java/xyz/wbsite/ai/TestSimpleChat.java
deleted file mode 100644
index 9982296..0000000
--- a/src/main/java/xyz/wbsite/ai/TestSimpleChat.java
+++ /dev/null
@@ -1,33 +0,0 @@
-package xyz.wbsite.ai;
-
-import dev.langchain4j.data.message.ChatMessage;
-import dev.langchain4j.data.message.UserMessage;
-import dev.langchain4j.model.chat.request.ChatRequest;
-import dev.langchain4j.model.chat.response.ChatResponse;
-import dev.langchain4j.model.openai.OpenAiChatModel;
-
-/**
- * 主函数入口
- */
-public class TestSimpleChat {
-
-    public static void main(String[] args) {
-        OpenAiChatModel model = OpenAiChatModel.builder()
-                .baseUrl("http://36.138.207.178:11434/v1")
-                .apiKey("1")
-                .modelName("deepseek-r1:14B")
-                .build();
-
-        String generate = model.chat("你好");
-        System.out.println(generate);
-
-        ChatRequest chatRequest = ChatRequest.builder()
-                .messages(new ChatMessage[]{
-                        UserMessage.from("你是谁")
-                })
-                .build();
-
-        ChatResponse chatResponse = model.chat(chatRequest);
-        System.out.println(chatResponse.aiMessage().text());
-    }
-}
\ No newline at end of file
diff --git a/src/main/java/xyz/wbsite/ai/TestStreamChat.java b/src/main/java/xyz/wbsite/ai/TestStreamChat.java
deleted file mode 100644
index eed13c7..0000000
--- a/src/main/java/xyz/wbsite/ai/TestStreamChat.java
+++ /dev/null
@@ -1,54 +0,0 @@
-package xyz.wbsite.ai;
-
-import cn.hutool.core.collection.CollUtil;
-import cn.hutool.core.thread.ThreadUtil;
-import dev.langchain4j.data.message.AiMessage;
-import dev.langchain4j.data.message.ChatMessage;
-import dev.langchain4j.data.message.UserMessage;
-import dev.langchain4j.model.StreamingResponseHandler;
-import dev.langchain4j.model.chat.response.ChatResponse;
-import dev.langchain4j.model.chat.response.StreamingChatResponseHandler;
-import dev.langchain4j.model.openai.OpenAiStreamingChatModel;
-import dev.langchain4j.model.output.Response;
-
-import java.util.List;
-
-/**
- * 主函数入口
- */
-public class TestStreamChat {
-
-    public static void main(String[] args) {
-        OpenAiStreamingChatModel model = OpenAiStreamingChatModel.builder()
-                .baseUrl("http://36.138.207.178:11434/v1")
-                .apiKey("1")
-                .modelName("deepseek-r1:14B")
-                .build();
-
-        List<ChatMessage> messages = CollUtil.newArrayList(
-                UserMessage.from("假如树上有10只鸟，10分钟前飞走了2只，5分钟前又飞回了1只，刚刚又来了3只，那现在树上有几只鸟?")
-        );
-
-        ThreadUtil.execAsync(new Runnable() {
-            @Override
-            public void run() {
-                model.chat(messages, new StreamingChatResponseHandler(){
-                    @Override
-                    public void onPartialResponse(String s) {
-                        System.out.print(s);
-                    }
-
-                    @Override
-                    public void onCompleteResponse(ChatResponse chatResponse) {
-                        System.out.println("onComplete");
-                    }
-
-                    @Override
-                    public void onError(Throwable throwable) {
-                        System.err.println(throwable.getMessage());
-                    }
-                });
-            }
-        });
-    }
-}
\ No newline at end of file