feat(data-process): 放宽问答生成数量上限

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

@@ -4,6 +4,10 @@ import type {
   PreprocessOption,
   StructuredProcessOptions,
 } from './types'
+import {
+  normalizeQaPairsGenerationCount,
+  QA_PAIRS_GENERATION_LIMITS,
+} from './types'
 import DatasetSplitEditor from './DatasetSplitEditor.vue'
 import GenerationOptionsPanel from './GenerationOptionsPanel.vue'
 
@@ -41,6 +45,10 @@ function updateGenerationOptions(value: GenerationControlOptions) {
   emit('update:options', { ...props.options, ...value })
 }
 
+function updateQaPairsPerRow(value: number | undefined) {
+  updateField('qaPairsPerRow', normalizeQaPairsGenerationCount(value))
+}
+
 function updatePreprocessOptions(value: Array<string | number | boolean>) {
   const allowedValues = new Set(PREPROCESS_OPTIONS.map((option) => option.value))
   const preprocessOptions = Array.from(new Set(value.filter(
@@ -97,15 +105,16 @@ function updatePreprocessOptions(value: Array<string | number | boolean>) {
       <div class="generation-option-row">
         <div class="generation-option-copy">
           <strong>每行生成数量</strong>
-          <small>每行结构化数据生成的问答对数量</small>
+          <small>支持 1～50 条；数量越大，处理耗时和 Token 消耗越高</small>
         </div>
         <el-input-number
           :model-value="options.qaPairsPerRow"
-          :min="1"
-          :max="5"
+          :min="QA_PAIRS_GENERATION_LIMITS.min"
+          :max="QA_PAIRS_GENERATION_LIMITS.max"
           :step="1"
+          :precision="0"
           controls-position="right"
-          @update:model-value="updateField('qaPairsPerRow', Number($event) || 1)"
+          @update:model-value="updateQaPairsPerRow"
         />
       </div>
       <DatasetSplitEditor

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

@@ -6,6 +6,7 @@ import type {
   UnstructuredPreprocessOption,
   UnstructuredProcessOptions,
 } from './types'
+import { QA_PAIRS_GENERATION_LIMITS } from './types'
 import DatasetSplitEditor from './DatasetSplitEditor.vue'
 import GenerationOptionsPanel from './GenerationOptionsPanel.vue'
 
@@ -40,7 +41,7 @@ const UNSTRUCTURED_NUMBER_LIMITS = {
   chunkOverlap: { min: 0, max: 500 },
   minChunkSize: { min: 20, max: 500 },
   semanticBreakpointPercentile: { min: 1, max: 99 },
-  qaPairsPerChunk: { min: 1, max: 3 },
+  qaPairsPerChunk: QA_PAIRS_GENERATION_LIMITS,
 } as const
 
 type UnstructuredNumberField = keyof typeof UNSTRUCTURED_NUMBER_LIMITS
@@ -285,12 +286,12 @@ defineExpose({ revealValidation })
       <div class="generation-option-row">
         <div class="generation-option-copy">
           <strong>每个切片生成数量</strong>
-          <small>每个内容切片最多生成 3 个不同角度的问答对</small>
+          <small>支持 1～50 条；数量越大，处理耗时和 Token 消耗越高</small>
         </div>
         <el-input-number
           :model-value="options.qaPairsPerChunk"
-          :min="1"
-          :max="3"
+          :min="QA_PAIRS_GENERATION_LIMITS.min"
+          :max="QA_PAIRS_GENERATION_LIMITS.max"
           :step="1"
           :precision="0"
           controls-position="right"

frontend/src/views/data-process/create/dataProcessCreateState.ts

@@ -7,6 +7,7 @@ import type {
   UnstructuredProcessOptions,
   ProcessType,
 } from './types'
+import { normalizeQaPairsGenerationCount } from './types'
 
 export const DEFAULT_GENERATION_PROMPT = '你是一名专业的数据生成助手。请根据输入内容生成准确、完整、可直接用于模型训练的问答数据。仅输出符合目标格式的内容，答案应事实清晰、语言自然，不要添加分析过程、说明或无关内容。'
 
@@ -128,7 +129,10 @@ export function createStructuredOptionsFromConfig(config: DataProcessConfig): St
       'semantic_enrichment',
       defaults.semanticEnrichment,
     )),
-    qaPairsPerRow: numberValue(config, 'qa_pairs_per_row', defaults.qaPairsPerRow),
+    qaPairsPerRow: normalizeQaPairsGenerationCount(
+      numberValue(config, 'qa_pairs_per_row', defaults.qaPairsPerRow),
+      defaults.qaPairsPerRow,
+    ),
     datasetSplit: datasetSplitValue(config, defaults.datasetSplit),
   }
 }
@@ -163,7 +167,10 @@ export function createUnstructuredOptionsFromConfig(config: DataProcessConfig):
       'semantic_enrichment',
       defaults.semanticEnrichment,
     )),
-    qaPairsPerChunk: numberValue(config, 'qa_pairs_per_chunk', defaults.qaPairsPerChunk),
+    qaPairsPerChunk: normalizeQaPairsGenerationCount(
+      numberValue(config, 'qa_pairs_per_chunk', defaults.qaPairsPerChunk),
+      defaults.qaPairsPerChunk,
+    ),
     datasetSplit: datasetSplitValue(config, defaults.datasetSplit),
   }
 }

frontend/src/views/data-process/create/types.ts

@@ -4,6 +4,17 @@ export type ProcessType = 'structured' | 'unstructured' | 'external'
 
 export type StepId = 'create' | 'model' | 'upload' | 'preview' | 'generate' | 'results'
 
+export const QA_PAIRS_GENERATION_LIMITS = { min: 1, max: 50 } as const
+
+export function normalizeQaPairsGenerationCount(value: unknown, fallback = 1): number {
+  const parsed = Number(value)
+  const normalized = Number.isFinite(parsed) ? Math.trunc(parsed) : fallback
+  return Math.min(
+    QA_PAIRS_GENERATION_LIMITS.max,
+    Math.max(QA_PAIRS_GENERATION_LIMITS.min, normalized),
+  )
+}
+
 export type PreprocessOption =
   | 'clean_invalid'
   | 'detect_structure'