feat(data-management): 添加数据集相似度推荐功能

- 在DatasetApplicationService中实现getSimilarDatasets方法，支持基于标签匹配的相似数据集推荐 - 新增normalizeSimilarLimit、normalizeTagNames、countSharedTags等辅助方法用于相似度计算 - 在DatasetRepository接口及其实现类中添加findSimilarByTags方法，支持数据库层面的标签匹配查询 - 在DatasetController中暴露/similar REST API端点，支持按需获取相似数据集 - 在前端Overview组件中展示相似数据集表格，包含名称、标签、类型、文件数和更新时间等信息 - 在DatasetDetail页面集成相似数据集获取逻辑，限制默认返回数量为4条 - 移除KnowledgeItem中的冗余title字段，统一使用其他标识信息 - 优化知识管理相关组件中的标题显示逻辑，移除硬编码标题值
2026-01-30 11:43:44 +08:00
parent c51cd2b6e4
commit c221666e67
12 changed files with 481 additions and 98 deletions
--- a/frontend/src/pages/DataManagement/dataset.api.ts
+++ b/frontend/src/pages/DataManagement/dataset.api.ts
@@ -1,4 +1,8 @@
-import { get, post, put, del, download } from "@/utils/request";
+import { get, post, put, del, download } from "@/utils/request";
+
+type RequestParams = Record<string, unknown>;
+type RequestPayload = Record<string, unknown>;
+type UploadChunkConfig = Record<string, unknown>;

 // 数据集统计接口
 export function getDatasetStatisticsUsingGet() {
@@ -10,24 +14,35 @@ export function queryDatasetStatisticsByIdUsingGet(id: string | number) {
 }

 // 查询数据集列表
-export function queryDatasetsUsingGet(params?: any) {
-  return get("/api/data-management/datasets", params);
-}
+export function queryDatasetsUsingGet(params?: RequestParams) {
+  return get("/api/data-management/datasets", params);
+}
+
+// 创建数据集
+export function createDatasetUsingPost(data: RequestPayload) {
+  return post("/api/data-management/datasets", data);
+}

-// 创建数据集
-export function createDatasetUsingPost(data: any) {
-  return post("/api/data-management/datasets", data);
-}
-
-// 根据ID获取数据集详情
-export function queryDatasetByIdUsingGet(id: string | number) {
-  return get(`/api/data-management/datasets/${id}`);
-}
+// 根据ID获取数据集详情
+export function queryDatasetByIdUsingGet(id: string | number) {
+  return get(`/api/data-management/datasets/${id}`);
+}
+
+// 获取相似数据集
+export function querySimilarDatasetsUsingGet(
+  id: string | number,
+  params?: { limit?: number }
+) {
+  return get(`/api/data-management/datasets/${id}/similar`, params);
+}

 // 更新数据集
-export function updateDatasetByIdUsingPut(id: string | number, data: any) {
-  return put(`/api/data-management/datasets/${id}`, data);
-}
+export function updateDatasetByIdUsingPut(
+  id: string | number,
+  data: RequestPayload
+) {
+  return put(`/api/data-management/datasets/${id}`, data);
+}

 // 删除数据集
 export function deleteDatasetByIdUsingDelete(id: string | number) {
@@ -40,19 +55,28 @@ export function downloadDatasetUsingGet(id: string | number) {
 }

 // 验证数据集
-export function validateDatasetUsingPost(id: string | number, data?: any) {
-  return post(`/api/data-management/datasets/${id}/validate`, data);
-}
+export function validateDatasetUsingPost(
+  id: string | number,
+  data?: RequestPayload
+) {
+  return post(`/api/data-management/datasets/${id}/validate`, data);
+}

 // 获取数据集文件列表
-export function queryDatasetFilesUsingGet(id: string | number, params?: any) {
-  return get(`/api/data-management/datasets/${id}/files`, params);
-}
+export function queryDatasetFilesUsingGet(
+  id: string | number,
+  params?: RequestParams
+) {
+  return get(`/api/data-management/datasets/${id}/files`, params);
+}

 // 上传数据集文件
-export function uploadDatasetFileUsingPost(id: string | number, data: any) {
-  return post(`/api/data-management/datasets/${id}/files`, data);
-}
+export function uploadDatasetFileUsingPost(
+  id: string | number,
+  data: RequestPayload
+) {
+  return post(`/api/data-management/datasets/${id}/files`, data);
+}

 // 新建数据集文件夹
 export function createDatasetDirectoryUsingPost(
@@ -104,34 +128,40 @@ export function deleteDatasetFileUsingDelete(
 }

 // 文件预览
-export function previewDatasetUsingGet(id: string | number, params?: any) {
-  return get(`/api/data-management/datasets/${id}/preview`, params);
-}
+export function previewDatasetUsingGet(
+  id: string | number,
+  params?: RequestParams
+) {
+  return get(`/api/data-management/datasets/${id}/preview`, params);
+}

 // 获取数据集标签
-export function queryDatasetTagsUsingGet(params?: any) {
-  return get("/api/data-management/tags", params);
-}
+export function queryDatasetTagsUsingGet(params?: RequestParams) {
+  return get("/api/data-management/tags", params);
+}

 // 创建数据集标签
-export function createDatasetTagUsingPost(data: any) {
-  return post("/api/data-management/tags", data);
-}
+export function createDatasetTagUsingPost(data: RequestPayload) {
+  return post("/api/data-management/tags", data);
+}

 // 更新数据集标签
-export function updateDatasetTagUsingPut(data: any) {
-  return put(`/api/data-management/tags`, data);
-}
+export function updateDatasetTagUsingPut(data: RequestPayload) {
+  return put(`/api/data-management/tags`, data);
+}

 // 删除数据集标签
-export function deleteDatasetTagUsingDelete(data: any) {
-  return del(`/api/data-management/tags`, data);
-}
+export function deleteDatasetTagUsingDelete(data: RequestPayload) {
+  return del(`/api/data-management/tags`, data);
+}

 // 数据集质量检查
-export function checkDatasetQualityUsingPost(id: string | number, data?: any) {
-  return post(`/api/data-management/datasets/${id}/quality-check`, data);
-}
+export function checkDatasetQualityUsingPost(
+  id: string | number,
+  data?: RequestPayload
+) {
+  return post(`/api/data-management/datasets/${id}/quality-check`, data);
+}

 // 获取数据集质量报告
 export function getDatasetQualityReportUsingGet(id: string | number) {
@@ -139,9 +169,12 @@ export function getDatasetQualityReportUsingGet(id: string | number) {
 }

 // 数据集分析
-export function analyzeDatasetUsingPost(id: string | number, data?: any) {
-  return post(`/api/data-management/datasets/${id}/analyze`, data);
-}
+export function analyzeDatasetUsingPost(
+  id: string | number,
+  data?: RequestPayload
+) {
+  return post(`/api/data-management/datasets/${id}/analyze`, data);
+}

 // 获取数据集分析结果
 export function getDatasetAnalysisUsingGet(id: string | number) {
@@ -149,27 +182,36 @@ export function getDatasetAnalysisUsingGet(id: string | number) {
 }

 // 导出数据集
-export function exportDatasetUsingPost(id: string | number, data: any) {
-  return post(`/api/data-management/datasets/${id}/export`, data);
-}
+export function exportDatasetUsingPost(
+  id: string | number,
+  data: RequestPayload
+) {
+  return post(`/api/data-management/datasets/${id}/export`, data);
+}

 // 复制数据集
-export function copyDatasetUsingPost(id: string | number, data: any) {
-  return post(`/api/data-management/datasets/${id}/copy`, data);
-}
+export function copyDatasetUsingPost(
+  id: string | number,
+  data: RequestPayload
+) {
+  return post(`/api/data-management/datasets/${id}/copy`, data);
+}

 // 获取数据集版本列表
-export function queryDatasetVersionsUsingGet(
-  id: string | number,
-  params?: any
-) {
-  return get(`/api/data-management/datasets/${id}/versions`, params);
-}
+export function queryDatasetVersionsUsingGet(
+  id: string | number,
+  params?: RequestParams
+) {
+  return get(`/api/data-management/datasets/${id}/versions`, params);
+}

 // 创建数据集版本
-export function createDatasetVersionUsingPost(id: string | number, data: any) {
-  return post(`/api/data-management/datasets/${id}/versions`, data);
-}
+export function createDatasetVersionUsingPost(
+  id: string | number,
+  data: RequestPayload
+) {
+  return post(`/api/data-management/datasets/${id}/versions`, data);
+}

 // 切换数据集版本
 export function switchDatasetVersionUsingPut(
@@ -193,25 +235,29 @@ export function deleteDatasetVersionUsingDelete(
 * 文件上传相关接口
 */

-export function preUploadUsingPost(id: string | number, data: any) {
-  return post(
-    `/api/data-management/datasets/${id}/files/upload/pre-upload`,
-    data
-  );
-}
-
-export function cancelUploadUsingPut(id) {
-  return put(
-    `/api/data-management/datasets/upload/cancel-upload/${id}`,
-    {},
-    { showLoading: false }
-  );
-}
-
-export function uploadFileChunkUsingPost(id: string | number, params, config) {
-  return post(
-    `/api/data-management/datasets/${id}/files/upload/chunk`,
-    params,
+export function preUploadUsingPost(id: string | number, data: RequestPayload) {
+  return post(
+    `/api/data-management/datasets/${id}/files/upload/pre-upload`,
+    data
+  );
+}
+
+export function cancelUploadUsingPut(id: string | number) {
+  return put(
+    `/api/data-management/datasets/upload/cancel-upload/${id}`,
+    {},
+    { showLoading: false }
+  );
+}
+
+export function uploadFileChunkUsingPost(
+  id: string | number,
+  params: RequestPayload,
+  config: UploadChunkConfig
+) {
+  return post(
+    `/api/data-management/datasets/${id}/files/upload/chunk`,
+    params,
    {
      showLoading: false,
      ...config,