feat: add paddleocr parser (#12513)

### What problem does this PR solve?

Add PaddleOCR as a new PDF parser.

### Type of change

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

web/src/components/layout-recognize-form-field.tsx

@@ -6,6 +6,7 @@ import { camelCase } from 'lodash';
 import { ReactNode, useMemo } from 'react';
 import { useFormContext } from 'react-hook-form';
 import { MinerUOptionsFormField } from './mineru-options-form-field';
+import { PaddleOCROptionsFormField } from './paddleocr-options-form-field';
 import { SelectWithSearch } from './originui/select-with-search';
 import {
   FormControl,
@@ -28,12 +29,14 @@ export function LayoutRecognizeFormField({
   optionsWithoutLLM,
   label,
   showMineruOptions = true,
+  showPaddleocrOptions = true,
 }: {
   name?: string;
   horizontal?: boolean;
   optionsWithoutLLM?: { value: string; label: string }[];
   label?: ReactNode;
   showMineruOptions?: boolean;
+  showPaddleocrOptions?: boolean;
 }) {
   const form = useFormContext();
 
@@ -113,6 +116,7 @@ export function LayoutRecognizeFormField({
               </div>
             </FormItem>
             {showMineruOptions && <MinerUOptionsFormField />}
+            {showPaddleocrOptions && <PaddleOCROptionsFormField />}
           </>
         );
       }}

web/src/components/paddleocr-options-form-field.tsx

@@ -0,0 +1,95 @@
+import { RAGFlowFormItem } from '@/components/ragflow-form';
+import { Input } from '@/components/ui/input';
+import { RAGFlowSelect } from '@/components/ui/select';
+import { LLMFactory } from '@/constants/llm';
+import { buildOptions } from '@/utils/form';
+import { useFormContext, useWatch } from 'react-hook-form';
+import { useTranslation } from 'react-i18next';
+
+const algorithmOptions = buildOptions(['PaddleOCR-VL']);
+
+export function PaddleOCROptionsFormField({
+  namePrefix = 'parser_config',
+}: {
+  namePrefix?: string;
+}) {
+  const form = useFormContext();
+  const { t } = useTranslation();
+  const buildName = (field: string) =>
+    namePrefix ? `${namePrefix}.${field}` : field;
+
+  const layoutRecognize = useWatch({
+    control: form.control,
+    name: 'parser_config.layout_recognize',
+  });
+
+  // Check if PaddleOCR is selected (the value contains 'PaddleOCR' or matches the factory name)
+  const isPaddleOCRSelected =
+    layoutRecognize?.includes(LLMFactory.PaddleOCR) ||
+    layoutRecognize?.toLowerCase()?.includes('paddleocr');
+
+  if (!isPaddleOCRSelected) {
+    return null;
+  }
+
+  return (
+    <div className="space-y-4 border-l-2 border-primary/30 pl-4 ml-2">
+      <div className="text-sm font-medium text-text-secondary">
+        {t('knowledgeConfiguration.paddleocrOptions', 'PaddleOCR Options')}
+      </div>
+
+      <RAGFlowFormItem
+        name={buildName('paddleocr_api_url')}
+        label={t('knowledgeConfiguration.paddleocrApiUrl', 'PaddleOCR API URL')}
+        tooltip={t(
+          'knowledgeConfiguration.paddleocrApiUrlTip',
+          'The API endpoint URL for PaddleOCR service',
+        )}
+        horizontal={true}
+      >
+        {(field) => (
+          <Input
+            {...field}
+            placeholder={t('knowledgeConfiguration.paddleocrApiUrlPlaceholder')}
+          />
+        )}
+      </RAGFlowFormItem>
+
+      <RAGFlowFormItem
+        name={buildName('paddleocr_access_token')}
+        label={t('knowledgeConfiguration.paddleocrAccessToken', 'AI Studio Access Token')}
+        tooltip={t(
+          'knowledgeConfiguration.paddleocrAccessTokenTip',
+          'Access token for PaddleOCR API (optional)',
+        )}
+        horizontal={true}
+      >
+        {(field) => (
+          <Input
+            {...field}
+            placeholder={t('knowledgeConfiguration.paddleocrAccessTokenPlaceholder')}
+          />
+        )}
+      </RAGFlowFormItem>
+
+      <RAGFlowFormItem
+        name={buildName('paddleocr_algorithm')}
+        label={t('knowledgeConfiguration.paddleocrAlgorithm', 'PaddleOCR Algorithm')}
+        tooltip={t(
+          'knowledgeConfiguration.paddleocrAlgorithmTip',
+          'Algorithm to use for PaddleOCR parsing',
+        )}
+        horizontal={true}
+      >
+        {(field) => (
+          <RAGFlowSelect
+            value={field.value || 'PaddleOCR-VL'}
+            onChange={field.onChange}
+            options={algorithmOptions}
+            placeholder={t('common.selectPlaceholder', 'Select value')}
+          />
+        )}
+      </RAGFlowFormItem>
+    </div>
+  );
+}

web/src/components/svg-icon.tsx

@@ -105,6 +105,7 @@ export const LlmIcon = ({
     LLMFactory.Gemini,
     LLMFactory.StepFun,
     LLMFactory.MinerU,
+    LLMFactory.PaddleOCR,
     // LLMFactory.DeerAPI,
   ];
   if (svgIcons.includes(name as LLMFactory)) {