feat(frontend): 更新三种切分模式与PDF定位

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

@@ -30,15 +30,16 @@ const SMART_PREPROCESS_OPTIONS: UnstructuredPreprocessOption[] = [
 ]
 
 const CHUNK_METHODS: Array<{ value: ChunkMethod; label: string }> = [
-  { value: 'structure', label: '文档结构' },
-  { value: 'fixed', label: '固定 Token' },
-  { value: 'custom', label: '自定义分隔符' },
+  { value: 'layout_hybrid', label: '版面结构混合切分' },
+  { value: 'semantic', label: '语义切分' },
+  { value: 'fixed', label: '固定 Token 切分' },
 ]
 
 const UNSTRUCTURED_NUMBER_LIMITS = {
   chunkSize: { min: 200, max: 2000 },
   chunkOverlap: { min: 0, max: 500 },
   minChunkSize: { min: 20, max: 500 },
+  semanticBreakpointPercentile: { min: 1, max: 99 },
   qaPairsPerChunk: { min: 1, max: 3 },
 } as const
 
@@ -160,7 +161,7 @@ defineExpose({ revealValidation })
     <div class="section-title-row">
       <div>
         <h3>切分选项</h3>
-        <p>按文档结构、固定 Token 或自定义分隔符拆分长文档</p>
+        <p>优先保留文档版面结构，也可按主题变化或固定 Token 切分</p>
       </div>
     </div>
 
@@ -179,7 +180,9 @@ defineExpose({ revealValidation })
             :value="method.value"
           />
         </el-select>
-        <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>
+        <small v-if="options.chunkMethod === 'layout_hybrid'">默认推荐，按标题、段落、列表和表格结构切分，并合并过短内容块</small>
+        <small v-else-if="options.chunkMethod === 'semantic'">根据相邻内容的语义变化寻找主题边界，适合长文章和知识材料</small>
+        <small v-else>按句子边界控制固定 Token 长度，速度快且结果稳定</small>
       </label>
 
       <label class="config-field">
@@ -235,17 +238,22 @@ defineExpose({ revealValidation })
           <small>过短的尾部内容会尽量并入前一个切片</small>
         </label>
 
-        <label v-if="options.chunkMethod === 'custom'" class="config-field">
-          <span class="config-field-label">自定义分隔符</span>
-          <el-input
-            :model-value="options.customDelimiter"
-            maxlength="40"
-            show-word-limit
-            placeholder="例如：--- 或 ###"
-            aria-label="自定义分隔符"
-            @update:model-value="updateField('customDelimiter', $event)"
-          />
-          <small>系统会优先在分隔符位置结束当前切片</small>
+        <label v-if="options.chunkMethod === 'semantic'" class="config-field">
+          <span class="config-field-label">语义断点百分位</span>
+          <span class="unit-input">
+            <el-input-number
+              :model-value="options.semanticBreakpointPercentile"
+              :min="1"
+              :max="99"
+              :step="1"
+              :precision="0"
+              controls-position="right"
+              aria-label="语义断点百分位"
+              @update:model-value="updateUnstructuredNumber('semanticBreakpointPercentile', $event)"
+            />
+            <span>%</span>
+          </span>
+          <small>百分位越低切片越多，推荐保持 95%</small>
         </label>
     </div>