Fix: Dataset parse logic (#12330)

### What problem does this PR solve? Fix: Dataset logic of parser ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
2025-12-31 17:15:32 +08:00 · 2025-12-30 19:53:00 +08:00
parent 2fccf3924d
commit a7e466142d
9 changed files with 126 additions and 76 deletions
--- a/web/src/components/originui/select-with-search.tsx
+++ b/web/src/components/originui/select-with-search.tsx
@ -109,6 +109,19 @@ export const SelectWithSearch = forwardRef<
      }
    }, [options, value]);

+    const showSearch = useMemo(() => {
+      if (Array.isArray(options) && options.length > 5) {
+        return true;
+      }
+      if (Array.isArray(options)) {
+        const optionsNum = options.reduce((acc, option) => {
+          return acc + (option?.options?.length || 0);
+        }, 0);
+        return optionsNum > 5;
+      }
+      return false;
+    }, [options]);
+
    const handleSelect = useCallback(
      (val: string) => {
        setValue(val);
@ -179,7 +192,7 @@ export const SelectWithSearch = forwardRef<
          align="start"
        >
          <Command className="p-5">
-            {options && options.length > 5 && (
+            {showSearch && (
              <CommandInput
                placeholder={t('common.search') + '...'}
                className=" placeholder:text-text-disabled"
--- a/web/src/locales/en.ts
+++ b/web/src/locales/en.ts
@ -147,6 +147,8 @@ Procedural Memory: Learned skills, habits, and automated procedures.`,
        action: 'Action',
      },
      config: {
+        memorySizeTooltip: `Accounts for each message's content + its embedding vector (≈ Content + Dimensions × 8 Bytes). 
+Example: A 1 KB message with 1024-dim embedding uses ~9 KB. The 5 MB default limit holds ~500 such messages.`,
        avatar: 'Avatar',
        description: 'Description',
        memorySize: 'Memory size',
--- a/web/src/locales/zh.ts
+++ b/web/src/locales/zh.ts
@ -124,7 +124,6 @@ export default {
        forgetMessageTip: '确定遗忘吗？',
        messageDescription: '记忆提取使用高级设置中的提示词和温度值进行配置。',
        copied: '已复制！',
-        contentEmbed: '内容嵌入',
        content: '内容',
        delMessageWarn: `遗忘后，代理将无法检索此消息。`,
        forgetMessage: '遗忘消息',
@ -138,6 +137,8 @@ export default {
        action: '操作',
      },
      config: {
+        memorySizeTooltip: `记录每条消息的内容 + 其嵌入向量（≈ 内容 + 维度 × 8 字节）。
+例如：一条带有 1024 维嵌入的 1 KB 消息大约使用 9 KB。5 MB 的默认限制大约可容纳 500 条此类消息。`,
        avatar: '头像',
        description: '描述',
        memorySize: '记忆大小',
--- a/web/src/pages/dataset/dataset/index.tsx
+++ b/web/src/pages/dataset/dataset/index.tsx
@ -79,6 +79,7 @@ export default function Dataset() {
    useRowSelection();

  const {
+    chunkNum,
    list,
    visible: reparseDialogVisible,
    hideModal: hideReparseDialogModal,
@ -218,7 +219,7 @@ export default function Dataset() {
            // hidden={isZeroChunk || isRunning}
            hidden={true}
            handleOperationIconClick={handleOperationIconClick}
-            chunk_num={0}
+            chunk_num={chunkNum}
            visible={reparseDialogVisible}
            hideModal={hideReparseDialogModal}
          ></ReparseDialog>
--- a/web/src/pages/dataset/dataset/parsing-status-cell.tsx
+++ b/web/src/pages/dataset/dataset/parsing-status-cell.tsx
@ -183,7 +183,7 @@ export function ParsingStatusCell({
      )}
      {reparseDialogVisible && (
        <ReparseDialog
-          hidden={isZeroChunk || isRunning}
+          hidden={isRunning}
          // hidden={false}
          handleOperationIconClick={handleOperationIconClick}
          chunk_num={chunk_num}
--- a/web/src/pages/dataset/dataset/reparse-dialog.tsx
+++ b/web/src/pages/dataset/dataset/reparse-dialog.tsx
@ -2,12 +2,14 @@ import { ConfirmDeleteDialog } from '@/components/confirm-delete-dialog';
 import {
  DynamicForm,
  DynamicFormRef,
+  FormFieldConfig,
  FormFieldType,
 } from '@/components/dynamic-form';
 import { Checkbox } from '@/components/ui/checkbox';
 import { DialogProps } from '@radix-ui/react-dialog';
-import { t } from 'i18next';
-import { memo, useCallback, useEffect, useRef } from 'react';
+import { memo, useCallback, useEffect, useRef, useState } from 'react';
+import { ControllerRenderProps } from 'react-hook-form';
+import { useTranslation } from 'react-i18next';

 export const ReparseDialog = memo(
  ({
@ -26,18 +28,77 @@ export const ReparseDialog = memo(
    hideModal: () => void;
    hidden?: boolean;
  }) => {
-    // const [formInstance, setFormInstance] = useState<DynamicFormRef | null>(
-    //   null,
-    // );
+    const [defaultValues, setDefaultValues] = useState<any>(null);
+    const [fields, setFields] = useState<FormFieldConfig[]>([]);
+    const { t } = useTranslation();
+    const handleOperationIconClickRef = useRef(handleOperationIconClick);
+    const hiddenRef = useRef(hidden);

-    // const formCallbackRef = useCallback((node: DynamicFormRef | null) => {
-    //   if (node) {
-    //     setFormInstance(node);
-    //     console.log('Form instance assigned:', node);
-    //   } else {
-    //     console.log('Form instance removed');
-    //   }
-    // }, []);
+    useEffect(() => {
+      handleOperationIconClickRef.current = handleOperationIconClick;
+      hiddenRef.current = hidden;
+    });
+
+    useEffect(() => {
+      if (hiddenRef.current) {
+        handleOperationIconClickRef.current();
+      }
+    }, []);
+    useEffect(() => {
+      setDefaultValues({
+        delete: chunk_num > 0,
+        apply_kb: false,
+      });
+      const deleteField = {
+        name: 'delete',
+        label: '',
+        type: FormFieldType.Checkbox,
+        render: (fieldProps: ControllerRenderProps) => (
+          <div className="flex items-center text-text-secondary p-5 border border-border-button rounded-lg">
+            <Checkbox
+              {...fieldProps}
+              checked={fieldProps.value}
+              onCheckedChange={(checked: boolean) => {
+                fieldProps.onChange(checked);
+              }}
+            />
+            <span className="ml-2">
+              {chunk_num > 0
+                ? t(`knowledgeDetails.redo`, {
+                    chunkNum: chunk_num,
+                  })
+                : t('knowledgeDetails.redoAll')}
+            </span>
+          </div>
+        ),
+      };
+      const applyKBField = {
+        name: 'apply_kb',
+        label: '',
+        type: FormFieldType.Checkbox,
+        defaultValue: false,
+        render: (fieldProps: ControllerRenderProps) => (
+          <div className="flex items-center text-text-secondary p-5 border border-border-button rounded-lg">
+            <Checkbox
+              {...fieldProps}
+              checked={fieldProps.value}
+              onCheckedChange={(checked: boolean) => {
+                fieldProps.onChange(checked);
+              }}
+            />
+            <span className="ml-2">
+              {t('knowledgeDetails.applyAutoMetadataSettings')}
+            </span>
+          </div>
+        ),
+      };
+      if (chunk_num > 0) {
+        setFields([deleteField, applyKBField]);
+      }
+      if (chunk_num <= 0) {
+        setFields([applyKBField]);
+      }
+    }, [chunk_num, t]);

    const formCallbackRef = useRef<DynamicFormRef>(null);

@ -68,12 +129,6 @@ export const ReparseDialog = memo(
      }
    }, [formCallbackRef, handleOperationIconClick]);

-    useEffect(() => {
-      if (hidden) {
-        handleOperationIconClick();
-      }
-    }, []);
-
    return (
      <ConfirmDeleteDialog
        title={t(`knowledgeDetails.parseFile`)}
@ -91,48 +146,8 @@ export const ReparseDialog = memo(
                  console.log('submit', data);
                }}
                ref={formCallbackRef}
-                fields={[
-                  {
-                    name: 'delete',
-                    label: '',
-                    type: FormFieldType.Checkbox,
-                    render: (fieldProps) => (
-                      <div className="flex items-center text-text-secondary p-5 border border-border-button rounded-lg">
-                        <Checkbox
-                          {...fieldProps}
-                          onCheckedChange={(checked: boolean) => {
-                            fieldProps.onChange(checked);
-                          }}
-                        />
-                        <span className="ml-2">
-                          {chunk_num > 0
-                            ? t(`knowledgeDetails.redo`, {
-                                chunkNum: chunk_num,
-                              })
-                            : t('knowledgeDetails.redoAll')}
-                        </span>
-                      </div>
-                    ),
-                  },
-                  {
-                    name: 'apply_kb',
-                    label: '',
-                    type: FormFieldType.Checkbox,
-                    render: (fieldProps) => (
-                      <div className="flex items-center text-text-secondary p-5 border border-border-button rounded-lg">
-                        <Checkbox
-                          {...fieldProps}
-                          onCheckedChange={(checked: boolean) => {
-                            fieldProps.onChange(checked);
-                          }}
-                        />
-                        <span className="ml-2">
-                          {t('knowledgeDetails.applyAutoMetadataSettings')}
-                        </span>
-                      </div>
-                    ),
-                  },
-                ]}
+                fields={fields}
+                defaultValues={defaultValues}
              >
                {/* <DynamicForm.CancelButton
                handleCancel={() => handleOperationIconClick(false)}
--- a/web/src/pages/dataset/dataset/use-bulk-operate-dataset.tsx
+++ b/web/src/pages/dataset/dataset/use-bulk-operate-dataset.tsx
@ -10,7 +10,7 @@ import {
 } from '@/hooks/use-document-request';
 import { IDocumentInfo } from '@/interfaces/database/document';
 import { Ban, CircleCheck, CircleX, Play, Trash2 } from 'lucide-react';
-import { useCallback } from 'react';
+import { useCallback, useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
 import { toast } from 'sonner';
 import { DocumentType, RunningStatus } from './constant';
@ -32,6 +32,16 @@ export function useBulkOperateDataset({
  const { setDocumentStatus } = useSetDocumentStatus();
  const { removeDocument } = useRemoveDocument();
  const { visible, showModal, hideModal } = useSetModalState();
+
+  const chunkNum = useMemo(() => {
+    if (!documents.length) {
+      return 0;
+    }
+    return documents.reduce((acc, cur) => {
+      return acc + cur.chunk_num;
+    }, 0);
+  }, [documents]);
+
  const runDocument = useCallback(
    async (run: number, option?: { delete: boolean; apply_kb: boolean }) => {
      const nonVirtualKeys = selectedRowKeys.filter(
@ -132,5 +142,5 @@ export function useBulkOperateDataset({
    },
  ];

-  return { list, visible, hideModal, showModal, handleRunClick };
+  return { chunkNum, list, visible, hideModal, showModal, handleRunClick };
 }
--- a/web/src/pages/dataset/process-log-modal.tsx
+++ b/web/src/pages/dataset/process-log-modal.tsx
@ -38,21 +38,27 @@ interface ProcessLogModalProps {
 }

 const InfoItem: React.FC<{
+  overflowTip?: boolean;
  label: string;
  value: string | React.ReactNode;
  className?: string;
-}> = ({ label, value, className = '' }) => {
+}> = ({ label, value, className = '', overflowTip = false }) => {
  return (
    <div className={`flex flex-col mb-4 ${className}`}>
      <span className="text-text-secondary text-sm">{label}</span>
-      <Tooltip>
-        <TooltipTrigger asChild>
-          <span className="text-text-primary mt-1 truncate w-full">
-            {value}
-          </span>
-        </TooltipTrigger>
-        <TooltipContent>{value}</TooltipContent>
-      </Tooltip>
+      {overflowTip && (
+        <Tooltip>
+          <TooltipTrigger asChild>
+            <span className="text-text-primary mt-1 truncate w-full">
+              {value}
+            </span>
+          </TooltipTrigger>
+          <TooltipContent>{value}</TooltipContent>
+        </Tooltip>
+      )}
+      {!overflowTip && (
+        <span className="text-text-primary mt-1 truncate w-full">{value}</span>
+      )}
    </div>
  );
 };
@ -139,6 +145,7 @@ const ProcessLogModal: React.FC<ProcessLogModalProps> = ({
            return (
              <div className="w-1/2" key={key}>
                <InfoItem
+                  overflowTip={true}
                  label={t(key)}
                  value={logInfo[key as keyof typeof logInfo]}
                />
--- a/web/src/pages/memory/memory-setting/memory-model-form.tsx
+++ b/web/src/pages/memory/memory-setting/memory-model-form.tsx
@ -92,6 +92,7 @@ export const MemoryModelForm = () => {
          label: t('memory.config.memorySize') + ' (Bytes)',
          type: FormFieldType.Number,
          horizontal: true,
+          tooltip: t('memory.config.memorySizeTooltip'),
          // placeholder: t('memory.config.memorySizePlaceholder'),
          required: false,
        }}