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-Hant/common.json

@@ -1,5 +1,6 @@
 {
   "App": "應用程式",
+  "Click_to_expand": "點擊查看詳情",
   "Download": "下載",
   "Export": "匯出",
   "FAQ.ai_point_a": "每次呼叫 AI 模型時，都會消耗一定數量的 AI 點數。詳細的計算標準請參考上方的「AI 點數計算標準」。\nToken 計算採用與 GPT3.5 相同的公式，1 Token ≈ 0.7 個中文字 ≈ 0.9 個英文單字，連續出現的字元可能會被視為 1 個 Token。",
@@ -537,6 +538,7 @@
   "core.dataset.collection.metadata.source name": "來源名稱",
   "core.dataset.collection.metadata.source size": "來源大小",
   "core.dataset.collection.status.active": "已就緒",
+  "core.dataset.collection.status.error": "訓練異常",
   "core.dataset.collection.sync.result.sameRaw": "內容未變更，無需更新",
   "core.dataset.collection.sync.result.success": "開始同步",
   "core.dataset.data.Data Content": "相關資料內容",

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

@@ -28,9 +28,24 @@
   "custom_data_process_params_desc": "自訂資料處理規則",
   "custom_split_sign_tip": "允許你根據自定義的分隔符進行分塊。\n通常用於已處理好的數據，使用特定的分隔符來精確分塊。\n可以使用 | 符號表示多個分割符，例如：“。|.” 表示中英文句號。\n\n盡量避免使用正則相關特殊符號，例如: * () [] {} 等。",
   "data_amount": "{{dataAmount}} 組數據, {{indexAmount}} 組索引",
+  "data_error_amount": "{{errorAmount}} 組訓練異常",
   "data_index_num": "索引 {{index}}",
   "data_process_params": "處理參數",
   "data_process_setting": "資料處理設定",
+  "dataset.Chunk_Number": "分塊號",
+  "dataset.Completed": "完成",
+  "dataset.Delete_Chunk": "刪除",
+  "dataset.Edit_Chunk": "編輯",
+  "dataset.Error_Message": "報錯信息",
+  "dataset.No_Error": "暫無異常信息",
+  "dataset.Operation": "操作",
+  "dataset.ReTrain": "重試",
+  "dataset.Training Process": "訓練狀態",
+  "dataset.Training_Count": "{{count}} 組訓練中",
+  "dataset.Training_Errors": "異常",
+  "dataset.Training_QA": "{{count}} 組問答對訓練中",
+  "dataset.Training_Status": "訓練狀態",
+  "dataset.Training_Waiting": "需等待 {{count}} 組數據",
   "dataset.Unsupported operation": "操作不支持",
   "dataset.no_collections": "尚無資料集",
   "dataset.no_tags": "尚無標籤",
@@ -82,6 +97,13 @@
   "preview_chunk_empty": "無法讀取該文件內容",
   "preview_chunk_intro": "共 {{total}} 個分塊，最多展示 10 個",
   "preview_chunk_not_selected": "點擊左側文件後進行預覽",
+  "process.Auto_Index": "自動索引生成",
+  "process.Get QA": "問答對提取",
+  "process.Image_Index": "圖片索引生成",
+  "process.Is_Ready": "已就緒",
+  "process.Parsing": "內容解析中",
+  "process.Vectorizing": "索引向量化",
+  "process.Waiting": "排隊中",
   "rebuild_embedding_start_tip": "切換索引模型任務已開始",
   "rebuilding_index_count": "重建中索引數量：{{count}}",
   "request_headers": "請求頭",
@@ -114,7 +136,10 @@
   "tag.total_tags": "共 {{total}} 個標籤",
   "the_knowledge_base_has_indexes_that_are_being_trained_or_being_rebuilt": "資料集有索引正在訓練或重建中",
   "total_num_files": "共 {{total}} 個文件",
+  "training.Error": "{{count}} 組異常",
+  "training.Normal": "正常",
   "training_mode": "分段模式",
+  "training_ready": "{{count}} 組",
   "vector_model_max_tokens_tip": "每個分塊數據，最大長度為 3000 tokens",
   "vllm_model": "圖片理解模型",
   "website_dataset": "網站同步",