refac: robust file upload failed handling

backend/open_webui/models/files.py

@@ -130,6 +130,17 @@ class FilesTable:
             except Exception:
                 return None
 
+    def get_file_by_id_and_user_id(self, id: str, user_id: str) -> Optional[FileModel]:
+        with get_db() as db:
+            try:
+                file = db.query(File).filter_by(id=id, user_id=user_id).first()
+                if file:
+                    return FileModel.model_validate(file)
+                else:
+                    return None
+            except Exception:
+                return None
+
     def get_file_metadata_by_id(self, id: str) -> Optional[FileMetadataResponse]:
         with get_db() as db:
             try:

backend/open_webui/routers/retrieval.py

@@ -1407,8 +1407,13 @@ def process_file(
     form_data: ProcessFileForm,
     user=Depends(get_verified_user),
 ):
-    try:
+    if user.role == "admin":
         file = Files.get_file_by_id(form_data.file_id)
+    else:
+        file = Files.get_file_by_id_and_user_id(form_data.file_id, user.id)
+
+    if file:
+        try:
 
             collection_name = form_data.collection_name
 
@@ -1421,7 +1426,9 @@ def process_file(
 
                 try:
                     # /files/{file_id}/data/content/update
-                VECTOR_DB_CLIENT.delete_collection(collection_name=f"file-{file.id}")
+                    VECTOR_DB_CLIENT.delete_collection(
+                        collection_name=f"file-{file.id}"
+                    )
                 except:
                     # Audio file upload pipeline
                     pass
@@ -1602,6 +1609,11 @@ def process_file(
 
         except Exception as e:
             log.exception(e)
+            Files.update_file_data_by_id(
+                file.id,
+                {"status": "failed"},
+            )
+
             if "No pandoc was found" in str(e):
                 raise HTTPException(
                     status_code=status.HTTP_400_BAD_REQUEST,
@@ -1613,6 +1625,11 @@ def process_file(
                     detail=str(e),
                 )
 
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
 
 class ProcessTextForm(BaseModel):
     name: str