feat(data-process): 优化上传切分流程与PDF高亮预览

frontend/src/views/data-process/create/UnstructuredOptionsPanel.vue

@@ -30,9 +30,8 @@ const SMART_PREPROCESS_OPTIONS: UnstructuredPreprocessOption[] = [
 ]
 
 const CHUNK_METHODS: Array<{ value: ChunkMethod; label: string }> = [
-  { value: 'semantic', label: '自动语义切分' },
-  { value: 'heading', label: '按标题和段落' },
-  { value: 'fixed', label: '按固定长度' },
+  { value: 'structure', label: '文档结构' },
+  { value: 'fixed', label: '固定 Token' },
   { value: 'custom', label: '自定义分隔符' },
 ]
 
@@ -70,9 +69,9 @@ function updateGenerationOptions(value: GenerationControlOptions) {
 
 function updateSmartPreprocess(value: string | number | boolean) {
   const enabled = Boolean(value)
-  const remainingOptions = props.options.preprocessOptions.filter(
+  const remainingOptions = Array.from(new Set(props.options.preprocessOptions.filter(
     (option) => !SMART_PREPROCESS_OPTIONS.includes(option),
-  )
+  )))
   updateField(
     'preprocessOptions',
     enabled ? [...SMART_PREPROCESS_OPTIONS, ...remainingOptions] : remainingOptions,
@@ -80,9 +79,11 @@ function updateSmartPreprocess(value: string | number | boolean) {
 }
 
 function updateDesensitize(value: string | number | boolean) {
-  const preprocessOptions: UnstructuredPreprocessOption[] = props.options.preprocessOptions.filter(
-    (option) => option !== 'desensitize',
-  )
+  const preprocessOptions: UnstructuredPreprocessOption[] = Array.from(new Set(
+    props.options.preprocessOptions.filter(
+      (option) => option !== 'desensitize',
+    ),
+  ))
   if (Boolean(value)) preprocessOptions.push('desensitize')
   updateField('preprocessOptions', preprocessOptions)
 }
@@ -116,7 +117,7 @@ defineExpose({ revealValidation })
     <div class="section-title-row">
       <div>
         <h3>预处理选项</h3>
-        <p>默认使用推荐策略，只需决定是否需要脱敏</p>
+        <p>默认启用结构感知的推荐策略，只需决定是否需要脱敏</p>
       </div>
     </div>
     <div class="preprocess-option-grid">
@@ -127,7 +128,7 @@ defineExpose({ revealValidation })
         />
         <span class="preprocess-option-copy">
           <strong>智能预处理</strong>
-          <small>自动清理、解析、去重及保留上下文</small>
+          <small>清理无效内容、感知文档结构、合并短块、预过滤低质量内容、近重复去重，并通过重叠保护上下文</small>
         </span>
       </label>
 
@@ -138,7 +139,7 @@ defineExpose({ revealValidation })
         />
         <span class="preprocess-option-copy">
           <strong>敏感信息脱敏</strong>
-          <small>处理姓名、手机号等隐私信息</small>
+          <small>识别并脱敏姓名、手机号、邮箱和身份证号</small>
         </span>
       </label>
 
@@ -159,7 +160,7 @@ defineExpose({ revealValidation })
     <div class="section-title-row">
       <div>
         <h3>切分选项</h3>
-        <p>以语义完整为优先，将长文档拆成可独立生成问答的内容块</p>
+        <p>按文档结构、固定 Token 或自定义分隔符拆分长文档</p>
       </div>
     </div>
 
@@ -178,7 +179,7 @@ defineExpose({ revealValidation })
             :value="method.value"
           />
         </el-select>
-        <small>推荐使用自动语义切分，在长度限制内优先保留完整句段</small>
+        <small>推荐使用文档结构，按标题、段落和句子边界保留完整内容块</small>
       </label>
 
       <label class="config-field">