mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-22 06:06:40 +08:00
Feature/mineru improvements (#11938)
我已在下面的评论中用中文重复说明。 ### What problem does this PR solve? ## Summary This PR enhances the MinerU document parser with additional configuration options, giving users more control over PDF parsing behavior and improving support for multilingual documents. ## Changes ### Backend (`deepdoc/parser/mineru_parser.py`) - Added configurable parsing options: - **Parse Method**: `auto`, `txt`, or `ocr` — allows users to choose the extraction strategy - **Formula Recognition**: Toggle for enabling/disabling formula extraction (useful to disable for Cyrillic documents where it may cause issues) - **Table Recognition**: Toggle for enabling/disabling table extraction - Added language code mapping (`LANGUAGE_TO_MINERU_MAP`) to translate RAGFlow language settings to MinerU-compatible language codes for better OCR accuracy - Improved parser configuration handling to pass these options through the processing pipeline ### Frontend (`web/`) - Created new `MinerUOptionsFormField` component that conditionally renders when MinerU is selected as the layout recognition engine - Added UI controls for: - Parse method selection (dropdown) - Formula recognition toggle (switch) - Table recognition toggle (switch) - Added i18n translations for English and Chinese - Integrated the options into both the dataset creation dialog and dataset settings page ### Integration - Updated `rag/app/naive.py` to forward MinerU options to the parser - Updated task service to handle the new configuration parameters ## Why MinerU is a powerful document parser, but the default settings don't work well for all document types. This PR allows users to: 1. Choose the best parsing method for their documents 2. Disable formula recognition for Cyrillic/non-Latin scripts where it causes issues 3. Control table extraction based on document needs 4. Benefit from automatic language detection for better OCR results ## Testing - [x] Tested MinerU parsing with different parse methods - [x] Verified UI renders correctly when MinerU is selected/deselected - [x] Confirmed settings persist correctly in dataset configuration ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [x] Refactoring - [ ] Performance Improvement - [ ] Other (please describe): --------- Co-authored-by: user210 <user210@rt> Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
@ -16,10 +16,18 @@ import {
|
||||
FormMessage,
|
||||
} from '@/components/ui/form';
|
||||
import { Input } from '@/components/ui/input';
|
||||
import {
|
||||
Select,
|
||||
SelectContent,
|
||||
SelectItem,
|
||||
SelectTrigger,
|
||||
SelectValue,
|
||||
} from '@/components/ui/select';
|
||||
import { LanguageTranslationMap } from '@/constants/common';
|
||||
import { FormLayout } from '@/constants/form';
|
||||
import { IModalProps } from '@/interfaces/common';
|
||||
import { zodResolver } from '@hookform/resolvers/zod';
|
||||
import { useEffect } from 'react';
|
||||
import { useEffect, useMemo } from 'react';
|
||||
import { useForm, useWatch } from 'react-hook-form';
|
||||
import { useTranslation } from 'react-i18next';
|
||||
import { z } from 'zod';
|
||||
@ -34,6 +42,13 @@ const FormId = 'dataset-creating-form';
|
||||
export function InputForm({ onOk }: IModalProps<any>) {
|
||||
const { t } = useTranslation();
|
||||
|
||||
const languageOptions = useMemo(() => {
|
||||
return Object.keys(LanguageTranslationMap).map((x) => ({
|
||||
label: x,
|
||||
value: x,
|
||||
}));
|
||||
}, []);
|
||||
|
||||
const FormSchema = z
|
||||
.object({
|
||||
name: z
|
||||
@ -51,6 +66,7 @@ export function InputForm({ onOk }: IModalProps<any>) {
|
||||
.trim(),
|
||||
parser_id: z.string().optional(),
|
||||
pipeline_id: z.string().optional(),
|
||||
language: z.string().optional(),
|
||||
})
|
||||
.superRefine((data, ctx) => {
|
||||
// When parseType === 1, parser_id is required
|
||||
@ -83,6 +99,7 @@ export function InputForm({ onOk }: IModalProps<any>) {
|
||||
parseType: 1,
|
||||
parser_id: '',
|
||||
embd_id: '',
|
||||
language: 'English',
|
||||
},
|
||||
});
|
||||
|
||||
@ -130,6 +147,33 @@ export function InputForm({ onOk }: IModalProps<any>) {
|
||||
)}
|
||||
/>
|
||||
|
||||
<FormField
|
||||
control={form.control}
|
||||
name="language"
|
||||
render={({ field }) => (
|
||||
<FormItem>
|
||||
<FormLabel>{t('common.language')}</FormLabel>
|
||||
<Select onValueChange={field.onChange} defaultValue={field.value}>
|
||||
<FormControl>
|
||||
<SelectTrigger>
|
||||
<SelectValue
|
||||
placeholder={t('common.languagePlaceholder')}
|
||||
/>
|
||||
</SelectTrigger>
|
||||
</FormControl>
|
||||
<SelectContent>
|
||||
{languageOptions.map((option) => (
|
||||
<SelectItem key={option.value} value={option.value}>
|
||||
{option.label}
|
||||
</SelectItem>
|
||||
))}
|
||||
</SelectContent>
|
||||
</Select>
|
||||
<FormMessage />
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
|
||||
<EmbeddingModelItem line={2} isEdit={false} />
|
||||
<ParseTypeItem />
|
||||
{parseType === 1 && <ChunkMethodItem></ChunkMethodItem>}
|
||||
|
||||
Reference in New Issue
Block a user