refac

backend/open_webui/models/knowledge.py

@@ -1069,6 +1069,26 @@ class KnowledgeTable:
         for child_id in child_ids:
             await self._delete_files_in_subtree(child_id, db=db)
 
+    async def get_files_by_id_and_directory_id(
+        self,
+        knowledge_id: str,
+        directory_id: str,
+        db: Optional[AsyncSession] = None,
+    ) -> list[FileModel]:
+        """Get all files in a directory and its subdirectories."""
+        async with get_async_db_context(db) as db:
+            directory_ids = [directory_id]
+            for parent_id in directory_ids:
+                result = await db.execute(select(KnowledgeDirectory.id).filter_by(parent_id=parent_id))
+                directory_ids.extend(result.scalars().all())
+            result = await db.execute(
+                select(File)
+                .join(KnowledgeFile, File.id == KnowledgeFile.file_id)
+                .filter(KnowledgeFile.knowledge_id == knowledge_id)
+                .filter(KnowledgeFile.directory_id.in_(directory_ids))
+            )
+            return [FileModel.model_validate(file) for file in result.scalars().all()]
+
     async def move_file_to_directory(
         self,
         knowledge_id: str,

backend/open_webui/routers/knowledge.py

@@ -1642,13 +1642,9 @@ async def remove_file_from_knowledge_by_id(
 
     # Remove content from the vector database
     try:
-        await ASYNC_VECTOR_DB_CLIENT.delete(
-            collection_name=knowledge.id, filter={'file_id': form_data.file_id}
-        )  # Remove by file_id first
-
-        await ASYNC_VECTOR_DB_CLIENT.delete(
-            collection_name=knowledge.id, filter={'hash': file.hash}
-        )  # Remove by hash as well in case of duplicates
+        await ASYNC_VECTOR_DB_CLIENT.delete(collection_name=knowledge.id, filter={'file_id': form_data.file_id})
+        if file.hash:
+            await ASYNC_VECTOR_DB_CLIENT.delete(collection_name=knowledge.id, filter={'hash': file.hash})
     except Exception as e:
         log.debug('This was most likely caused by bypassing embedding processing')
         log.debug(e)
@@ -1988,7 +1984,8 @@ async def sync_knowledge_cleanup(
 
         try:
             await ASYNC_VECTOR_DB_CLIENT.delete(collection_name=id, filter={'file_id': file_id})
-            await ASYNC_VECTOR_DB_CLIENT.delete(collection_name=id, filter={'hash': file.hash})
+            if file.hash:
+                await ASYNC_VECTOR_DB_CLIENT.delete(collection_name=id, filter={'hash': file.hash})
         except Exception:
             pass
 
@@ -2321,6 +2318,9 @@ async def delete_knowledge_directory(
             detail=ERROR_MESSAGES.NOT_FOUND,
         )
 
+    # Collect before delete_directory drops the KnowledgeFile rows
+    files = [] if move_files else await Knowledges.get_files_by_id_and_directory_id(id, dir_id, db=db)
+
     success = await Knowledges.delete_directory(
         directory_id=dir_id,
         move_files_to_parent=move_files,
@@ -2331,6 +2331,23 @@ async def delete_knowledge_directory(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             detail='Failed to delete directory.',
         )
+
+    for file in files:
+        try:
+            await ASYNC_VECTOR_DB_CLIENT.delete(collection_name=id, filter={'file_id': file.id})
+            if file.hash:
+                await ASYNC_VECTOR_DB_CLIENT.delete(collection_name=id, filter={'hash': file.hash})
+        except Exception as e:
+            log.debug('This was most likely caused by bypassing embedding processing')
+            log.debug(e)
+
+        if (
+            not ENABLE_KNOWLEDGE_FILE_RETENTION
+            and not await Knowledges.get_knowledges_by_file_id(file.id, db=db)
+            and (file.user_id == user.id or user.role == 'admin')
+        ):
+            await delete_file_resource(file, db)
+
     await publish_event(
         request,
         EVENTS.KNOWLEDGE_DIRECTORY_DELETED,