Training status (#4424)

* dataset data training state (#4311)

* dataset data training state

* fix

* fix ts

* fix

* fix api format

* fix

* fix

* perf: count training

* format

* fix: dataset training state (#4417)

* fix

* add test

* fix

* fix

* fix test

* fix test

* perf: training count

* count

* loading status

---------

Co-authored-by: heheer <heheer@sealos.io>

packages/web/i18n/zh-CN/common.json

@@ -1,5 +1,6 @@
 {
   "App": "应用",
+  "Click_to_expand": "点击查看详情",
   "Download": "下载",
   "Export": "导出",
   "FAQ.ai_point_a": "每次调用AI模型时，都会消耗一定的AI积分。具体的计算标准可参考上方的“AI 积分计算标准”。\nToken计算采用GPT3.5相同公式，1Token≈0.7中文字符≈0.9英文单词，连续出现的字符可能被认为是1个Tokens。",
@@ -541,6 +542,7 @@
   "core.dataset.collection.metadata.source name": "来源名",
   "core.dataset.collection.metadata.source size": "来源大小",
   "core.dataset.collection.status.active": "已就绪",
+  "core.dataset.collection.status.error": "训练异常",
   "core.dataset.collection.sync.result.sameRaw": "内容未变动，无需更新",
   "core.dataset.collection.sync.result.success": "开始同步",
   "core.dataset.data.Data Content": "相关数据内容",

packages/web/i18n/zh-CN/dataset.json

@@ -28,9 +28,24 @@
   "custom_data_process_params_desc": "自定义设置数据处理规则",
   "custom_split_sign_tip": "允许你根据自定义的分隔符进行分块。通常用于已处理好的数据，使用特定的分隔符来精确分块。可以使用 | 符号表示多个分割符，例如：“。|.” 表示中英文句号。\n尽量避免使用正则相关特殊符号，例如: * () [] {} 等。",
   "data_amount": "{{dataAmount}} 组数据, {{indexAmount}} 组索引",
+  "data_error_amount": "{{errorAmount}} 组训练异常",
   "data_index_num": "索引 {{index}}",
   "data_process_params": "处理参数",
   "data_process_setting": "数据处理配置",
+  "dataset.Chunk_Number": "分块号",
+  "dataset.Completed": "完成",
+  "dataset.Delete_Chunk": "删除",
+  "dataset.Edit_Chunk": "编辑",
+  "dataset.Error_Message": "报错信息",
+  "dataset.No_Error": "暂无异常信息",
+  "dataset.Operation": "操作",
+  "dataset.ReTrain": "重试",
+  "dataset.Training Process": "训练状态",
+  "dataset.Training_Count": "{{count}} 组训练中",
+  "dataset.Training_Errors": "异常 ({{count}})",
+  "dataset.Training_QA": "{{count}} 组问答对训练中",
+  "dataset.Training_Status": "训练状态",
+  "dataset.Training_Waiting": "需等待 {{count}} 组数据",
   "dataset.Unsupported operation": "操作不支持",
   "dataset.no_collections": "暂无数据集",
   "dataset.no_tags": "暂无标签",
@@ -82,6 +97,14 @@
   "preview_chunk_empty": "无法读取该文件内容",
   "preview_chunk_intro": "共 {{total}} 个分块，最多展示 10 个",
   "preview_chunk_not_selected": "点击左侧文件后进行预览",
+  "process.Auto_Index": "自动索引生成",
+  "process.Get QA": "问答对提取",
+  "process.Image_Index": "图片索引生成",
+  "process.Is_Ready": "已就绪",
+  "process.Is_Ready_Count": "{{count}} 组已就绪",
+  "process.Parsing": "内容解析中",
+  "process.Vectorizing": "索引向量化",
+  "process.Waiting": "排队中",
   "rebuild_embedding_start_tip": "切换索引模型任务已开始",
   "rebuilding_index_count": "重建中索引数量：{{count}}",
   "request_headers": "请求头参数，会自动补充 Bearer",
@@ -114,7 +137,10 @@
   "tag.total_tags": "共{{total}}个标签",
   "the_knowledge_base_has_indexes_that_are_being_trained_or_being_rebuilt": "知识库有训练中或正在重建的索引",
   "total_num_files": "共 {{total}} 个文件",
+  "training.Error": "{{count}} 组异常",
+  "training.Normal": "正常",
   "training_mode": "处理方式",
+  "training_ready": "{{count}} 组",
   "vector_model_max_tokens_tip": "每个分块数据，最大长度为 3000 tokens",
   "vllm_model": "图片理解模型",
   "website_dataset": "Web 站点同步",