diff --git a/backend/open_webui/retrieval/loaders/main.py b/backend/open_webui/retrieval/loaders/main.py
index 54f71d7234..f86f6fc2dc 100644
--- a/backend/open_webui/retrieval/loaders/main.py
+++ b/backend/open_webui/retrieval/loaders/main.py
@@ -27,7 +27,7 @@ from open_webui.retrieval.loaders.datalab_marker import DatalabMarkerLoader
 from open_webui.retrieval.loaders.external_document import ExternalDocumentLoader
 from open_webui.retrieval.loaders.mineru import MinerULoader
 from open_webui.retrieval.loaders.mistral import MistralLoader
-from open_webui.retrieval.loaders.paddleocr_vl import PaddleOCRVLLoader
+from open_webui.retrieval.loaders.paddleocr_vl import PADDLEOCR_VL_SUPPORTED_EXTENSIONS, PaddleOCRVLLoader
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
@@ -556,7 +556,12 @@ class Loader:
                 use_base64=self.kwargs.get('MISTRAL_OCR_USE_BASE64', False),
                 user=self.user,
             )
-        elif self.engine == 'paddleocr_vl' and self.kwargs.get('PADDLEOCR_VL_TOKEN') != '':
+        elif (
+            self.engine == 'paddleocr_vl'
+            and self.kwargs.get('PADDLEOCR_VL_BASE_URL')
+            and self.kwargs.get('PADDLEOCR_VL_TOKEN')
+            and file_ext in PADDLEOCR_VL_SUPPORTED_EXTENSIONS
+        ):
             loader = PaddleOCRVLLoader(
                 api_url=self.kwargs.get('PADDLEOCR_VL_BASE_URL'),
                 token=self.kwargs.get('PADDLEOCR_VL_TOKEN'),
diff --git a/backend/open_webui/retrieval/loaders/paddleocr_vl.py b/backend/open_webui/retrieval/loaders/paddleocr_vl.py
index 40c185eab6..50172ddb47 100644
--- a/backend/open_webui/retrieval/loaders/paddleocr_vl.py
+++ b/backend/open_webui/retrieval/loaders/paddleocr_vl.py
@@ -11,6 +11,9 @@ from open_webui.env import GLOBAL_LOG_LEVEL
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
 
+PADDLEOCR_VL_IMAGE_EXTENSIONS = ['png', 'jpg', 'jpeg', 'bmp', 'tiff', 'webp']
+PADDLEOCR_VL_SUPPORTED_EXTENSIONS = ['pdf'] + PADDLEOCR_VL_IMAGE_EXTENSIONS
+
 
 class PaddleOCRVLLoader:
     """Loader that uses PaddleOCR-vl API to extract text from PDF/images."""
@@ -46,8 +49,7 @@ class PaddleOCRVLLoader:
 
         # Detect fileType based on file extension
         ext = self.file_path.lower().split('.')[-1]
-        image_extensions = ['png', 'jpg', 'jpeg', 'bmp', 'tiff', 'webp']
-        file_type = 1 if ext in image_extensions else 0
+        file_type = 1 if ext in PADDLEOCR_VL_IMAGE_EXTENSIONS else 0
 
         payload = {
             'file': file_data,