feat: Marker api content extraction support

backend/open_webui/retrieval/loaders/main.py

@@ -21,7 +21,7 @@ from langchain_community.document_loaders import (
 )
 from langchain_core.documents import Document
 
-
+from open_webui.retrieval.loaders.datalab_marker_loader import DatalabMarkerLoader
 from open_webui.retrieval.loaders.external_document import ExternalDocumentLoader
 from open_webui.retrieval.loaders.mistral import MistralLoader
 
@@ -236,6 +236,23 @@ class Loader:
                     mime_type=file_content_type,
                     extract_images=self.kwargs.get("PDF_EXTRACT_IMAGES"),
                 )
+        elif (
+            self.engine == "datalab_marker"
+            and self.kwargs.get("DATALAB_MARKER_API_KEY")
+            and file_ext in ["pdf", "xls", "xlsx", "ods", "doc", "docx", "odt", "ppt", "pptx", "odp", "html", "epub", "png", "jpeg", "jpg", "webp", "gif", "tiff"]
+        ):
+            loader = DatalabMarkerLoader(
+                file_path=file_path,
+                api_key=self.kwargs["DATALAB_MARKER_API_KEY"],
+                langs=self.kwargs.get("DATALAB_MARKER_LANGS"),
+                use_llm=self.kwargs.get("DATALAB_MARKER_USE_LLM", False),
+                skip_cache=self.kwargs.get("DATALAB_MARKER_SKIP_CACHE", False),
+                force_ocr=self.kwargs.get("DATALAB_MARKER_FORCE_OCR", False),
+                paginate=self.kwargs.get("DATALAB_MARKER_PAGINATE", False),
+                strip_existing_ocr=self.kwargs.get("DATALAB_MARKER_STRIP_EXISTING_OCR", False),
+                disable_image_extraction=self.kwargs.get("DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION", False),
+                output_format=self.kwargs.get("DATALAB_MARKER_OUTPUT_FORMAT", "markdown")
+            )
         elif self.engine == "docling" and self.kwargs.get("DOCLING_SERVER_URL"):
             if self._is_text_file(file_ext, file_content_type):
                 loader = TextLoader(file_path, autodetect_encoding=True)