feat: 添加项目配置和依赖更新

配置更新： 1. 前端配置 - 添加 hook-fetch 依赖用于 HTTP 请求 - 更新 vite.config.mts 配置 - 添加 .npmrc 配置文件 2. 后端配置 - 更新 application.yml 和 application-dev.yml 配置 - 更新 docker-compose.yml 配置 3. 代码优化 - OSS 客户端优化 - SSE 管理器优化 - 聊天服务和向量存储策略优化 4. 项目文档 - 添加 CLAUDE.md 项目指南 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-02 09:44:56 +00:00
parent ac8e6ca088
commit 2f25a943b8
14 changed files with 584 additions and 98 deletions
--- a/hzhub-ai/hzhub-admin/src/main/resources/application-dev.yml
+++ b/hzhub-ai/hzhub-admin/src/main/resources/application-dev.yml
@@ -58,7 +58,7 @@ spring:
          driverClassName: com.mysql.cj.jdbc.Driver
          # jdbc 所有参数配置参考 https://lionli.blog.csdn.net/article/details/122018562
          # rewriteBatchedStatements=true 批处理优化 大幅提升批量插入更新删除性能(对数据库有性能损耗 使用批量操作应考虑性能问题)
-          url: jdbc:mysql://127.0.0.1:3306/hzhub_ai?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8&autoReconnect=true&rewriteBatchedStatements=true&allowPublicKeyRetrieval=true&nullCatalogMeansCurrent=true
+          url: jdbc:mysql://127.0.0.1:3306/ruoyi_ai?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8&autoReconnect=true&rewriteBatchedStatements=true&allowPublicKeyRetrieval=true&nullCatalogMeansCurrent=true
          username: root
          password: hzhub123
 #        agent:
--- a/hzhub-ai/hzhub-admin/src/main/resources/application.yml
+++ b/hzhub-ai/hzhub-admin/src/main/resources/application.yml
@@ -277,11 +277,11 @@ warm-flow:
 vector-store:
  # 向量存储类型 可选(weaviate/milvus)
  # 如需修改向量库类型，请修改此配置值!
-  type: milvus
+  type: weaviate
  # Weaviate配置
  weaviate:
    protocol: http
-    host: 127.0.0.1:6038
+    host: 127.0.0.1:28080
    classname: LocalKnowledge
  # Milvus配置
  milvus:
--- a/hzhub-ai/hzhub-common/hzhub-common-oss/src/main/java/org/hzhub/common/oss/core/OssClient.java
+++ b/hzhub-ai/hzhub-common/hzhub-common-oss/src/main/java/org/hzhub/common/oss/core/OssClient.java
@@ -15,6 +15,7 @@ import org.hzhub.common.oss.properties.OssProperties;
 import software.amazon.awssdk.auth.credentials.AwsBasicCredentials;
 import software.amazon.awssdk.auth.credentials.StaticCredentialsProvider;
 import software.amazon.awssdk.core.async.*;
+import software.amazon.awssdk.core.client.config.ClientOverrideConfiguration;
 import software.amazon.awssdk.http.nio.netty.NettyNioAsyncHttpClient;
 import software.amazon.awssdk.regions.Region;
 import software.amazon.awssdk.services.s3.S3AsyncClient;
@@ -94,7 +95,14 @@ public class OssClient {
                .region(of())
                .forcePathStyle(isStyle)
                .httpClient(NettyNioAsyncHttpClient.builder()
-                    .connectionTimeout(Duration.ofSeconds(60)).build())
+                    .connectionTimeout(Duration.ofMinutes(5))
+                    .readTimeout(Duration.ofMinutes(5))
+                    .writeTimeout(Duration.ofMinutes(5))
+                    .build())
+                .overrideConfiguration(ClientOverrideConfiguration.builder()
+                    .apiCallTimeout(Duration.ofMinutes(10))
+                    .apiCallAttemptTimeout(Duration.ofMinutes(5))
+                    .build())
                .build();

            //AWS基于 CRT 的 S3 AsyncClient 实例用作 S3 传输管理器的底层客户端
@@ -172,36 +180,22 @@ public class OssClient {
     * @throws OssException 如果上传失败，抛出自定义异常
     */
    public UploadResult upload(InputStream inputStream, String key, Long length, String contentType) {
-        // 如果输入流不是 ByteArrayInputStream，则将其读取为字节数组再创建 ByteArrayInputStream
-        if (!(inputStream instanceof ByteArrayInputStream)) {
-            inputStream = new ByteArrayInputStream(IoUtil.readBytes(inputStream));
-        }
+        // 将输入流转换为字节数组，使用异步字节数组上传方式
        try {
-            // 创建异步请求体（length如果为空会报错）
-            BlockingInputStreamAsyncRequestBody body = BlockingInputStreamAsyncRequestBody.builder()
-                .contentLength(length)
-                .subscribeTimeout(Duration.ofSeconds(120))
-                .build();
+            byte[] bytes = IoUtil.readBytes(inputStream);

-            // 使用 transferManager 进行上传
-            Upload upload = transferManager.upload(
-                x -> x.requestBody(body).addTransferListener(LoggingTransferListener.create())
-                    .putObjectRequest(
-                        y -> y.bucket(properties.getBucketName())
-                            .key(key)
-                            .contentType(contentType)
-                            // 用于设置对象的访问控制列表（ACL）。不同云厂商对ACL的支持和实现方式有所不同，
-                            // 因此根据具体的云服务提供商，你可能需要进行不同的配置（自行开启，阿里云有acl权限配置，腾讯云没有acl权限配置）
-                            //.acl(getAccessPolicy().getObjectCannedACL())
-                            .build())
-                    .build());
+            // 使用异步方式上传字节数组
+            software.amazon.awssdk.services.s3.model.PutObjectResponse response = client.putObject(
+                software.amazon.awssdk.services.s3.model.PutObjectRequest.builder()
+                    .bucket(properties.getBucketName())
+                    .key(key)
+                    .contentType(contentType)
+                    .contentLength((long) bytes.length)
+                    .build(),
+                software.amazon.awssdk.core.async.AsyncRequestBody.fromBytes(bytes)
+            ).join();

-            // 将输入流写入请求体
-            body.writeInputStream(inputStream);
-
-            // 等待文件上传操作完成
-            CompletedUpload uploadResult = upload.completionFuture().join();
-            String eTag = uploadResult.response().eTag();
+            String eTag = response.eTag();

            // 提取上传结果中的 ETag，并构建一个自定义的 UploadResult 对象
            return UploadResult.builder().url(getUrl() + StringUtils.SLASH + key).filename(key).eTag(eTag).build();
--- a/hzhub-ai/hzhub-common/hzhub-common-sse/src/main/java/org/hzhub/common/sse/core/SseEmitterManager.java
+++ b/hzhub-ai/hzhub-common/hzhub-common-sse/src/main/java/org/hzhub/common/sse/core/SseEmitterManager.java
@@ -93,6 +93,24 @@ public class SseEmitterManager {
        return emitter;
    }

+    /**
+     * 获取已存在的 SSE 连接（不创建新连接）
+     *
+     * @param userId 用户的唯一标识符
+     * @param token  用户的唯一令牌
+     * @return 返回已存在的 SseEmitter 实例，如果不存在则返回 null
+     */
+    public SseEmitter getEmitter(Long userId, String token) {
+        if (userId == null || token == null) {
+            return null;
+        }
+        Map<String, SseEmitter> emitters = USER_TOKEN_EMITTERS.get(userId);
+        if (MapUtil.isNotEmpty(emitters)) {
+            return emitters.get(token);
+        }
+        return null;
+    }
+
    /**
     * 断开指定用户的 SSE 连接
     *
--- a/hzhub-ai/hzhub-modules/hzhub-chat/src/main/java/org/hzhub/service/chat/impl/ChatServiceFacade.java
+++ b/hzhub-ai/hzhub-modules/hzhub-chat/src/main/java/org/hzhub/service/chat/impl/ChatServiceFacade.java
@@ -105,10 +105,17 @@ public class ChatServiceFacade implements IChatService {
     */
    public SseEmitter sseChat(ChatRequest chatRequest) {

-        // 4. 具体的服务实现
+        // 获取用户信息和已存在的 SSE 连接
        Long userId = LoginHelper.getUserId();
        String tokenValue = StpUtil.getTokenValue();
-        SseEmitter emitter = sseEmitterManager.connect(userId, tokenValue);
+
+        // 获取已存在的 SSE 连接（前端已通过 GET /resource/sse 建立）
+        // 不再调用 connect() 以避免关闭前端的连接
+        SseEmitter emitter = sseEmitterManager.getEmitter(userId, tokenValue);
+        if (emitter == null) {
+            // 如果没有已存在的连接，则建立新连接（兼容未预先建立连接的情况）
+            emitter = sseEmitterManager.connect(userId, tokenValue);
+        }

        // 1. 根据模型名称查询完整配置
        ChatModelVo chatModelVo = chatModelService.selectModelByName(chatRequest.getModel());
@@ -205,66 +212,81 @@ public class ChatServiceFacade implements IChatService {
     * @param chatModelVo      聊天模型配置
     */
    private void handleThinkingMode(ChatRequest chatRequest, List<ChatMessage> contextMessages, ChatModelVo chatModelVo) {
-        // 步骤1: 配置MCP传输层 - 连接到bing-cn-mcp服务器
-        McpTransport transport = new StdioMcpTransport.Builder()
-            .command(List.of("C:\\Program Files\\nodejs\\npx.cmd", "-y", "bing-cn-mcp"))
-            .logEvents(true)
-            .build();
+        try {
+            // 步骤1: 配置MCP传输层 - 连接到bing-cn-mcp服务器
+            // 根据操作系统选择正确的命令路径
+            String osName = System.getProperty("os.name").toLowerCase();
+            List<String> mcpCommand = osName.contains("win")
+                ? List.of("C:\\Program Files\\nodejs\\npx.cmd", "-y", "bing-cn-mcp")
+                : List.of("npx", "-y", "bing-cn-mcp");

-        McpClient mcpClient = new DefaultMcpClient.Builder()
-            .transport(transport)
-            .build();
+            McpTransport transport = new StdioMcpTransport.Builder()
+                .command(mcpCommand)
+                .logEvents(true)
+                .build();

-        ToolProvider toolProvider = McpToolProvider.builder()
-            .mcpClients(List.of(mcpClient))
-            .build();
+            McpClient mcpClient = new DefaultMcpClient.Builder()
+                .transport(transport)
+                .build();

-        // 配置echarts MCP
-        McpTransport transport1 = new StdioMcpTransport.Builder()
-            .command(List.of("C:\\Program Files\\nodejs\\npx.cmd", "-y", "mcp-echarts"))
-            .logEvents(true)
-            .build();
+            ToolProvider toolProvider = McpToolProvider.builder()
+                .mcpClients(List.of(mcpClient))
+                .build();

-        McpClient mcpClient1 = new DefaultMcpClient.Builder()
-            .transport(transport1)
-            .build();
+            // 配置echarts MCP
+            List<String> echartsCommand = osName.contains("win")
+                ? List.of("C:\\Program Files\\nodejs\\npx.cmd", "-y", "mcp-echarts")
+                : List.of("npx", "-y", "mcp-echarts");

-        ToolProvider toolProvider1 = McpToolProvider.builder()
-            .mcpClients(List.of(mcpClient1))
-            .build();
+            McpTransport transport1 = new StdioMcpTransport.Builder()
+                .command(echartsCommand)
+                .logEvents(true)
+                .build();

-        // 配置模型
-        OpenAiChatModel plannerModel = OpenAiChatModel.builder()
-            .baseUrl(chatModelVo.getApiHost())
-            .apiKey(chatModelVo.getApiKey())
-            .modelName(chatModelVo.getModelName())
-            .build();
+            McpClient mcpClient1 = new DefaultMcpClient.Builder()
+                .transport(transport1)
+                .build();

-        // 构建各Agent
-        SqlAgent sqlAgent = AgenticServices.agentBuilder(SqlAgent.class)
-            .chatModel(plannerModel)
-            .tools(new QueryAllTablesTool(), new QueryTableSchemaTool(), new ExecuteSqlQueryTool())
-            .build();
+            ToolProvider toolProvider1 = McpToolProvider.builder()
+                .mcpClients(List.of(mcpClient1))
+                .build();

-        WebSearchAgent searchAgent = AgenticServices.agentBuilder(WebSearchAgent.class)
-            .chatModel(plannerModel)
-            .toolProvider(toolProvider)
-            .build();
+            // 配置模型
+            OpenAiChatModel plannerModel = OpenAiChatModel.builder()
+                .baseUrl(chatModelVo.getApiHost())
+                .apiKey(chatModelVo.getApiKey())
+                .modelName(chatModelVo.getModelName())
+                .build();

-        ChartGenerationAgent chartGenerationAgent = AgenticServices.agentBuilder(ChartGenerationAgent.class)
-            .chatModel(plannerModel)
-            .toolProvider(toolProvider1)
-            .build();
+            // 构建各Agent
+            SqlAgent sqlAgent = AgenticServices.agentBuilder(SqlAgent.class)
+                .chatModel(plannerModel)
+                .tools(new QueryAllTablesTool(), new QueryTableSchemaTool(), new ExecuteSqlQueryTool())
+                .build();

-        // 构建监督者Agent
-        SupervisorAgent supervisor = AgenticServices.supervisorBuilder()
-            .chatModel(plannerModel)
-            .subAgents(sqlAgent, chartGenerationAgent)
-            .responseStrategy(SupervisorResponseStrategy.LAST)
-            .build();
+            WebSearchAgent searchAgent = AgenticServices.agentBuilder(WebSearchAgent.class)
+                .chatModel(plannerModel)
+                .toolProvider(toolProvider)
+                .build();

-        String invoke = supervisor.invoke(chatRequest.getContent());
-        contextMessages.add(AiMessage.from(invoke));
+            ChartGenerationAgent chartGenerationAgent = AgenticServices.agentBuilder(ChartGenerationAgent.class)
+                .chatModel(plannerModel)
+                .toolProvider(toolProvider1)
+                .build();
+
+            // 构建监督者Agent
+            SupervisorAgent supervisor = AgenticServices.supervisorBuilder()
+                .chatModel(plannerModel)
+                .subAgents(sqlAgent, chartGenerationAgent)
+                .responseStrategy(SupervisorResponseStrategy.LAST)
+                .build();
+
+            String invoke = supervisor.invoke(chatRequest.getContent());
+            contextMessages.add(AiMessage.from(invoke));
+        } catch (Exception e) {
+            log.error("深度思考模式执行失败: {}", e.getMessage(), e);
+            throw new RuntimeException("深度思考模式执行失败，请检查 MCP 服务是否正确配置: " + e.getMessage(), e);
+        }
    }

    /**
--- a/hzhub-ai/hzhub-modules/hzhub-chat/src/main/java/org/hzhub/service/chat/impl/provider/OllamaServiceImpl.java
+++ b/hzhub-ai/hzhub-modules/hzhub-chat/src/main/java/org/hzhub/service/chat/impl/provider/OllamaServiceImpl.java
@@ -9,6 +9,8 @@ import org.springframework.stereotype.Service;
 import org.hzhub.common.chat.domain.dto.request.ChatRequest;
 import org.hzhub.common.chat.domain.vo.chat.ChatModelVo;

+import java.time.Duration;
+
 /**
 * OllamaAI服务调用
 *
@@ -24,6 +26,7 @@ public class OllamaServiceImpl implements AbstractChatService {
        return OllamaStreamingChatModel.builder()
                .baseUrl(chatModelVo.getApiHost())
                .modelName(chatModelVo.getModelName())
+                .timeout(Duration.ofMinutes(3)) // 设置 3 分钟超时，适应本地模型较长的响应时间
                .build();
    }

--- a/hzhub-ai/hzhub-modules/hzhub-chat/src/main/java/org/hzhub/service/vector/impl/MilvusVectorStoreStrategy.java
+++ b/hzhub-ai/hzhub-modules/hzhub-chat/src/main/java/org/hzhub/service/vector/impl/MilvusVectorStoreStrategy.java
@@ -65,7 +65,11 @@ public class MilvusVectorStoreStrategy extends AbstractVectorStoreStrategy {
     */
    private int getModelDimension(String modelName) {
        ChatModelVo modelConfig = chatModelService.selectModelByName(modelName);
-        return modelConfig.getModelDimension();
+        Integer dimension = modelConfig.getModelDimension();
+        if (dimension == null) {
+            throw new IllegalArgumentException("模型 " + modelName + " 的维度配置为空，请在数据库中配置正确的 model_dimension 值");
+        }
+        return dimension;
    }

    @Override
--- a/hzhub-ai/hzhub-modules/hzhub-chat/src/main/java/org/hzhub/service/vector/impl/WeaviateVectorStoreStrategy.java
+++ b/hzhub-ai/hzhub-modules/hzhub-chat/src/main/java/org/hzhub/service/vector/impl/WeaviateVectorStoreStrategy.java
@@ -100,25 +100,73 @@ public class WeaviateVectorStoreStrategy extends AbstractVectorStoreStrategy {
        String docId = storeEmbeddingBo.getDocId();
        log.info("向量存储条数记录: {}", chunkList.size());
        long startTime = System.currentTimeMillis();
+        int successCount = 0;
+        int skipCount = 0;
+
        for (int i = 0; i < chunkList.size(); i++) {
            String text = chunkList.get(i);
            String fid = fidList.get(i);
-            Embedding embedding = embeddingModel.embed(text).content();
-            Map<String, Object> properties = Map.of(
-                    "text", text,
-                    "fid", fid,
-                    "kid", kid,
-                    "docId", docId
-            );
-            Float[] vector = toObjectArray(embedding.vector());
-            client.data().creator()
-                    .withClassName("LocalKnowledge" + kid)
-                    .withProperties(properties)
-                    .withVector(vector)
-                    .run();
+
+            // 跳过空文本或仅包含空白字符的文本
+            if (text == null || text.trim().isEmpty()) {
+                log.warn("跳过空文本块，索引: {}, fid: {}", i, fid);
+                skipCount++;
+                continue;
+            }
+
+            // 文本预处理：移除控制字符和特殊字符
+            text = text.replaceAll("[\\x00-\\x08\\x0B\\x0C\\x0E-\\x1F\\x7F]", "")
+                       .replaceAll("\\s+", " ")
+                       .trim();
+
+            if (text.isEmpty()) {
+                log.warn("文本预处理后为空，跳过，索引: {}, fid: {}", i, fid);
+                skipCount++;
+                continue;
+            }
+
+            try {
+                Embedding embedding = embeddingModel.embed(text).content();
+
+                // 检查 embedding 是否包含 NaN
+                float[] vectorData = embedding.vector();
+                boolean hasNaN = false;
+                for (float v : vectorData) {
+                    if (Float.isNaN(v) || Float.isInfinite(v)) {
+                        hasNaN = true;
+                        break;
+                    }
+                }
+
+                if (hasNaN) {
+                    log.error("Embedding 向量包含 NaN 或 Infinite 值，跳过该文本块，索引: {}, 文本长度: {}", i, text.length());
+                    skipCount++;
+                    continue;
+                }
+
+                Map<String, Object> properties = Map.of(
+                        "text", text,
+                        "fid", fid,
+                        "kid", kid,
+                        "docId", docId
+                );
+                Float[] vector = toObjectArray(embedding.vector());
+                client.data().creator()
+                        .withClassName("LocalKnowledge" + kid)
+                        .withProperties(properties)
+                        .withVector(vector)
+                        .run();
+                successCount++;
+
+            } catch (Exception e) {
+                log.error("处理文本块失败，索引: {}, fid: {}, 错误: {}", i, fid, e.getMessage());
+                skipCount++;
+                // 继续处理下一个文本块，不中断整个流程
+            }
        }
+
        long endTime = System.currentTimeMillis();
-        log.info("向量存储完成消耗时间：" + (endTime - startTime) / 1000 + "秒");
+        log.info("向量存储完成，成功: {}, 跳过: {}, 消耗时间: {}秒", successCount, skipCount, (endTime - startTime) / 1000);
    }