Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423)

### What problem does this PR solve?

#9869

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
This commit is contained in:
Kevin Hu
2025-10-09 12:36:19 +08:00
committed by GitHub
parent ef0aecea3b
commit cbf04ee470
490 changed files with 10630 additions and 30688 deletions

View File

@ -1,9 +1,11 @@
import { LlmModelType } from '@/constants/knowledge';
import { useTranslate } from '@/hooks/common-hooks';
import { useSelectLlmOptionsByModelType } from '@/hooks/llm-hooks';
import { cn } from '@/lib/utils';
import { camelCase } from 'lodash';
import { useMemo } from 'react';
import { ReactNode, useMemo } from 'react';
import { useFormContext } from 'react-hook-form';
import { SelectWithSearch } from './originui/select-with-search';
import {
FormControl,
FormField,
@ -11,24 +13,36 @@ import {
FormLabel,
FormMessage,
} from './ui/form';
import { RAGFlowSelect } from './ui/select';
export const enum DocumentType {
export const enum ParseDocumentType {
DeepDOC = 'DeepDOC',
PlainText = 'Plain Text',
}
export function LayoutRecognizeFormField() {
export function LayoutRecognizeFormField({
name = 'parser_config.layout_recognize',
horizontal = true,
optionsWithoutLLM,
label,
}: {
name?: string;
horizontal?: boolean;
optionsWithoutLLM?: { value: string; label: string }[];
label?: ReactNode;
}) {
const form = useFormContext();
const { t } = useTranslate('knowledgeDetails');
const allOptions = useSelectLlmOptionsByModelType();
const options = useMemo(() => {
const list = [DocumentType.DeepDOC, DocumentType.PlainText].map((x) => ({
label: x === DocumentType.PlainText ? t(camelCase(x)) : 'DeepDoc',
value: x,
}));
const list = optionsWithoutLLM
? optionsWithoutLLM
: [ParseDocumentType.DeepDOC, ParseDocumentType.PlainText].map((x) => ({
label:
x === ParseDocumentType.PlainText ? t(camelCase(x)) : 'DeepDoc',
value: x,
}));
const image2TextList = allOptions[LlmModelType.Image2text].map((x) => {
return {
@ -48,38 +62,40 @@ export function LayoutRecognizeFormField() {
});
return [...list, ...image2TextList];
}, [allOptions, t]);
}, [allOptions, optionsWithoutLLM, t]);
return (
<FormField
control={form.control}
name="parser_config.layout_recognize"
name={name}
render={({ field }) => {
if (typeof field.value === 'undefined') {
// default value set
form.setValue(
'parser_config.layout_recognize',
form.formState.defaultValues?.parser_config?.layout_recognize ??
'DeepDOC',
);
}
return (
<FormItem className=" items-center space-y-0 ">
<div className="flex items-center">
<FormItem className={'items-center space-y-0 '}>
<div
className={cn('flex', {
'flex-col ': !horizontal,
'items-center': horizontal,
})}
>
<FormLabel
tooltip={t('layoutRecognizeTip')}
className="text-sm text-muted-foreground whitespace-wrap w-1/4"
className={cn('text-sm text-muted-foreground whitespace-wrap', {
['w-1/4']: horizontal,
})}
>
{t('layoutRecognize')}
{label || t('layoutRecognize')}
</FormLabel>
<div className="w-3/4">
<div className={horizontal ? 'w-3/4' : 'w-full'}>
<FormControl>
<RAGFlowSelect {...field} options={options}></RAGFlowSelect>
<SelectWithSearch
{...field}
options={options}
></SelectWithSearch>
</FormControl>
</div>
</div>
<div className="flex pt-1">
<div className="w-1/4"></div>
<div className={horizontal ? 'w-1/4' : 'w-full'}></div>
<FormMessage />
</div>
</FormItem>