enh: PDF_LOADER_MODE

backend/open_webui/config.py

@@ -2809,6 +2809,12 @@ PDF_EXTRACT_IMAGES = PersistentConfig(
     os.environ.get("PDF_EXTRACT_IMAGES", "False").lower() == "true",
 )
 
+PDF_LOADER_MODE = PersistentConfig(
+    "PDF_LOADER_MODE",
+    "rag.pdf_loader_mode",
+    os.environ.get("PDF_LOADER_MODE", "page"),
+)
+
 RAG_EMBEDDING_MODEL = PersistentConfig(
     "RAG_EMBEDDING_MODEL",
     "rag.embedding_model",

backend/open_webui/main.py

@@ -288,6 +288,7 @@ from open_webui.config import (
     ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER,
     TIKTOKEN_ENCODING_NAME,
     PDF_EXTRACT_IMAGES,
+    PDF_LOADER_MODE,
     YOUTUBE_LOADER_LANGUAGE,
     YOUTUBE_LOADER_PROXY_URL,
     # Retrieval (Web Search)
@@ -944,6 +945,7 @@ app.state.config.RAG_OLLAMA_BASE_URL = RAG_OLLAMA_BASE_URL
 app.state.config.RAG_OLLAMA_API_KEY = RAG_OLLAMA_API_KEY
 
 app.state.config.PDF_EXTRACT_IMAGES = PDF_EXTRACT_IMAGES
+app.state.config.PDF_LOADER_MODE = PDF_LOADER_MODE
 
 app.state.config.YOUTUBE_LOADER_LANGUAGE = YOUTUBE_LOADER_LANGUAGE
 app.state.config.YOUTUBE_LOADER_PROXY_URL = YOUTUBE_LOADER_PROXY_URL

backend/open_webui/retrieval/loaders/main.py

@@ -361,7 +361,9 @@ class Loader:
         else:
             if file_ext == "pdf":
                 loader = PyPDFLoader(
-                    file_path, extract_images=self.kwargs.get("PDF_EXTRACT_IMAGES")
+                    file_path,
+                    extract_images=self.kwargs.get("PDF_EXTRACT_IMAGES"),
+                    mode=self.kwargs.get("PDF_LOADER_MODE", "page"),
                 )
             elif file_ext == "csv":
                 loader = CSVLoader(file_path, autodetect_encoding=True)

backend/open_webui/routers/retrieval.py

@@ -468,6 +468,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         # Content extraction settings
         "CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
         "PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
+        "PDF_LOADER_MODE": request.app.state.config.PDF_LOADER_MODE,
         "DATALAB_MARKER_API_KEY": request.app.state.config.DATALAB_MARKER_API_KEY,
         "DATALAB_MARKER_API_BASE_URL": request.app.state.config.DATALAB_MARKER_API_BASE_URL,
         "DATALAB_MARKER_ADDITIONAL_CONFIG": request.app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG,
@@ -659,6 +660,7 @@ class ConfigForm(BaseModel):
     # Content extraction settings
     CONTENT_EXTRACTION_ENGINE: Optional[str] = None
     PDF_EXTRACT_IMAGES: Optional[bool] = None
+    PDF_LOADER_MODE: Optional[str] = None
 
     DATALAB_MARKER_API_KEY: Optional[str] = None
     DATALAB_MARKER_API_BASE_URL: Optional[str] = None
@@ -786,6 +788,11 @@ async def update_rag_config(
         if form_data.PDF_EXTRACT_IMAGES is not None
         else request.app.state.config.PDF_EXTRACT_IMAGES
     )
+    request.app.state.config.PDF_LOADER_MODE = (
+        form_data.PDF_LOADER_MODE
+        if form_data.PDF_LOADER_MODE is not None
+        else request.app.state.config.PDF_LOADER_MODE
+    )
     request.app.state.config.DATALAB_MARKER_API_KEY = (
         form_data.DATALAB_MARKER_API_KEY
         if form_data.DATALAB_MARKER_API_KEY is not None
@@ -1180,6 +1187,7 @@ async def update_rag_config(
         # Content extraction settings
         "CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
         "PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
+        "PDF_LOADER_MODE": request.app.state.config.PDF_LOADER_MODE,
         "DATALAB_MARKER_API_KEY": request.app.state.config.DATALAB_MARKER_API_KEY,
         "DATALAB_MARKER_API_BASE_URL": request.app.state.config.DATALAB_MARKER_API_BASE_URL,
         "DATALAB_MARKER_ADDITIONAL_CONFIG": request.app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG,

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

@@ -362,6 +362,30 @@
 									</div>
 								</div>
 							</div>
+
+							<div class="flex w-full mt-2">
+								<div class="flex-1 flex justify-between">
+									<div class=" self-center text-xs font-medium">
+										<Tooltip
+											content={$i18n.t(
+												'Page mode creates one document per page. Single mode combines all pages into one document for better chunking across page boundaries.'
+											)}
+											placement="top-start"
+										>
+											{$i18n.t('PDF Loader Mode')}
+										</Tooltip>
+									</div>
+									<div class="">
+										<select
+											class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 text-xs bg-transparent outline-hidden text-right"
+											bind:value={RAGConfig.PDF_LOADER_MODE}
+										>
+											<option value="page">{$i18n.t('Page')}</option>
+											<option value="single">{$i18n.t('Single')}</option>
+										</select>
+									</div>
+								</div>
+							</div>
 						{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'datalab_marker'}
 							<div class="my-0.5 flex gap-2 pr-2">
 								<Tooltip