feat: add PaddleOCR-vl loader support and implement retrieval router infrastructure (#23945)

Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com>

src/lib/components/admin/Settings/Documents.svelte

@@ -184,6 +184,13 @@
 			toast.error($i18n.t('Mistral OCR API Key required.'));
 			return;
 		}
+		if (
+			RAGConfig.CONTENT_EXTRACTION_ENGINE === 'paddleocr_vl' &&
+			RAGConfig.PADDLEOCR_VL_BASE_URL === ''
+		) {
+			toast.error($i18n.t('PaddleOCR-vl API URL required.'));
+			return;
+		}
 
 		if (
 			RAGConfig.CONTENT_EXTRACTION_ENGINE === 'mineru' &&
@@ -356,6 +363,7 @@
 									<option value="datalab_marker">{$i18n.t('Datalab Marker API')}</option>
 									<option value="document_intelligence">{$i18n.t('Document Intelligence')}</option>
 									<option value="mistral_ocr">{$i18n.t('Mistral OCR')}</option>
+									<option value="paddleocr_vl">{$i18n.t('PaddleOCR-vl')}</option>
 									<option value="mineru">{$i18n.t('MinerU')}</option>
 								</select>
 							</div>
@@ -657,6 +665,19 @@
 									bind:value={RAGConfig.MISTRAL_OCR_API_KEY}
 								/>
 							</div>
+						{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'paddleocr_vl'}
+							<div class="my-0.5 flex gap-2 pr-2">
+								<input
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
+									placeholder={$i18n.t('Enter PaddleOCR-vl API Base URL')}
+									bind:value={RAGConfig.PADDLEOCR_VL_BASE_URL}
+								/>
+								<SensitiveInput
+									placeholder={$i18n.t('Enter PaddleOCR-vl API Token')}
+									bind:value={RAGConfig.PADDLEOCR_VL_TOKEN}
+									required={false}
+								/>
+							</div>
 						{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'mineru'}
 							<!-- API Mode Selection -->
 							<div class="flex w-full mt-2">

src/lib/i18n/locales/en-US/translation.json

@@ -775,6 +775,8 @@
 	"Enter prompt here.": "",
 	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter reasoning effort": "",
+	"Enter PaddleOCR-vl API Token": "",
+	"Enter PaddleOCR-vl API Base URL": "",
 	"Enter Score": "",
 	"Enter SearchApi API Key": "",
 	"Enter SearchApi Engine": "",
@@ -1518,6 +1520,7 @@
 	"Output format": "",
 	"Output Format": "",
 	"Overview": "",
+	"PaddleOCR-vl": "",
 	"page": "",
 	"Page": "",
 	"Page mode creates one document per page. Single mode combines all pages into one document for better chunking across page boundaries.": "",

src/lib/i18n/locales/zh-CN/translation.json

@@ -774,6 +774,8 @@
 	"Enter prompt here.": "在此输入提示词。",
 	"Enter proxy URL (e.g. https://user:password@host:port)": "输入代理地址（例如：https://用户名:密码@主机名:端口）",
 	"Enter reasoning effort": "输入推理努力",
+	"Enter PaddleOCR-vl API Token": "输入 PaddleOCR-vl 接口密钥",
+	"Enter PaddleOCR-vl API Base URL": "输入 PaddleOCR-vl API 基础地址",
 	"Enter Score": "输入评分",
 	"Enter SearchApi API Key": "输入 SearchApi 接口密钥",
 	"Enter SearchApi Engine": "输入 SearchApi 引擎",
@@ -1517,6 +1519,7 @@
 	"Output format": "输出格式",
 	"Output Format": "输出格式",
 	"Overview": "概述",
+	"PaddleOCR-vl": "PaddleOCR-vl",
 	"page": "页",
 	"Page": "页模式",
 	"Page mode creates one document per page. Single mode combines all pages into one document for better chunking across page boundaries.": "页模式将为每个页面创建一个文档；单文档模式则将所有页面合并为一个文档，以便更好地进行跨页分块。",