Feat: Q&A format segmentation support (#668)

Co-authored-by: jyong <718720800@qq.com>
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>

web/i18n/lang/dataset-creation.en.ts

@@ -73,6 +73,8 @@ const translation = {
     click: 'Go to settings',
     economical: 'Economical',
     economicalTip: 'Use offline vector engines, keyword indexes, etc. to reduce accuracy without spending tokens',
+    QATitle: 'Segmenting in Question & Answer format',
+    QATip: 'Enable this option will consume more tokens',
     emstimateCost: 'Estimation',
     emstimateSegment: 'Estimated segments',
     segmentCount: 'segments',
@@ -92,6 +94,9 @@ const translation = {
     sideTipP3: 'Cleaning removes unnecessary characters and formats, making datasets cleaner and easier to parse.',
     sideTipP4: 'Proper segmentation and cleaning improve model performance, providing more accurate and valuable results.',
     previewTitle: 'Preview',
+    previewButton: 'Switching to Q&A format',
+    previewSwitchTipStart: 'The current segment preview is in text format, switching to a question-and-answer format preview will',
+    previewSwitchTipEnd: ' consume additional tokens',
     characters: 'characters',
     indexSettedTip: 'To change the index method, please go to the ',
     datasetSettingLink: 'dataset settings.',

web/i18n/lang/dataset-creation.zh.ts

@@ -73,6 +73,8 @@ const translation = {
     click: '前往设置',
     economical: '经济',
     economicalTip: '使用离线的向量引擎、关键词索引等方式，降低了准确度但无需花费 Token',
+    QATitle: '采用 Q&A 分段模式',
+    QATip: '开启后将会消耗额外的 token',
     emstimateCost: '执行嵌入预估消耗',
     emstimateSegment: '预估分段数',
     segmentCount: '段',
@@ -92,6 +94,9 @@ const translation = {
     sideTipP3: '清洗则是对文本进行预处理，删除不必要的字符、符号或格式，使数据集更加干净、整洁，便于模型解析。',
     sideTipP4: '通过对数据集进行适当的分段和清洗，可以提高模型在实际应用中的表现，从而为用户提供更准确、更有价值的结果。',
     previewTitle: '分段预览',
+    previewButton: '切换至 Q&A 形式',
+    previewSwitchTipStart: '当前分段预览是文本模式，切换到 Q&A 模式将会',
+    previewSwitchTipEnd: '消耗额外的 token',
     characters: '字符',
     indexSettedTip: '要更改索引方法，请转到',
     datasetSettingLink: '数据集设置。',

web/i18n/lang/dataset-documents.en.ts

@@ -17,6 +17,7 @@ const translation = {
     action: {
       uploadFile: 'Upload new file',
       settings: 'Segment settings',
+      add: 'Add new segment',
       archive: 'Archive',
       delete: 'Delete',
       enableWarning: 'Archived file cannot be enabled',
@@ -310,6 +311,14 @@ const translation = {
     characters: 'characters',
     hitCount: 'hit count',
     vectorHash: 'Vector hash: ',
+    questionPlaceholder: 'add question here',
+    questionEmpty: 'Question can not be empty',
+    answerPlaceholder: 'add answer here',
+    answerEmpty: 'Answer can not be empty',
+    contentPlaceholder: 'add content here',
+    contentEmpty: 'Content can not be empty',
+    newTextSegment: 'New Text Segment',
+    newQaSegment: 'New Q&A Segment',
   },
 }
 

web/i18n/lang/dataset-documents.zh.ts

@@ -17,6 +17,7 @@ const translation = {
     action: {
       uploadFile: '上传新文件',
       settings: '分段设置',
+      add: '添加新分段',
       archive: '归档',
       delete: '删除',
       enableWarning: '归档的文件无法启用',
@@ -309,6 +310,14 @@ const translation = {
     characters: '字符',
     hitCount: '命中次数',
     vectorHash: '向量哈希：',
+    questionPlaceholder: '在这里添加问题',
+    questionEmpty: '问题不能为空',
+    answerPlaceholder: '在这里添加答案',
+    answerEmpty: '答案不能为空',
+    contentPlaceholder: '在这里添加内容',
+    contentEmpty: '内容不能为空',
+    newTextSegment: '新文本分段',
+    newQaSegment: '新问答分段',
   },
 }