refac

backend/open_webui/retrieval/utils.py

@@ -37,6 +37,7 @@ from open_webui.env import (
 from open_webui.models.access_grants import AccessGrants
 from open_webui.models.chats import Chats
 from open_webui.models.files import Files
+from open_webui.models.folders import Folders
 from open_webui.models.knowledge import Knowledges
 from open_webui.models.notes import Notes
 from open_webui.models.config import Config
@@ -48,6 +49,7 @@ from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
 from open_webui.retrieval.vector.main import GetResult, SearchResult
 from open_webui.retrieval.web.utils import get_web_loader
 from open_webui.utils.access_control.files import has_access_to_file
+from open_webui.utils.access_control.folders import has_folder_access
 from open_webui.utils.headers import include_user_info_headers
 from open_webui.utils.misc import get_message_list
 
@@ -1323,6 +1325,25 @@ async def get_sources_from_items(
     bypass_embedding_and_retrieval = await Config.get('rag.bypass_embedding_and_retrieval')
     extracted_collections = []
     query_results = []
+    folder_items = set()
+    expanded_folders = set()
+
+    items = list(items)
+    for item in items:
+        if item.get('type') != 'folder' or not user:
+            continue
+        folder_id = item.get('id')
+        if not folder_id or folder_id in expanded_folders:
+            continue
+        expanded_folders.add(folder_id)
+
+        folder = await Folders.get_folder_by_id(folder_id)
+        if folder and (user.role == 'admin' or await has_folder_access(user.id, folder, 'read', db=None)):
+            files = (folder.data or {}).get('files', [])
+            folder_items.update(
+                (entry.get('type'), entry.get('id')) for entry in files if isinstance(entry, dict)
+            )
+            items.extend(files)
 
     for item in items:
         query_result = None
@@ -1429,6 +1450,7 @@ async def get_sources_from_items(
                         user.role == 'admin'
                         or file_object.user_id == user.id
                         or await has_access_to_file(item.get('id'), 'read', user)
+                        or ('file', item.get('id')) in folder_items
                     ):
                         query_result = {
                             'documents': [[file_object.data.get('content', '')]],
@@ -1459,6 +1481,7 @@ async def get_sources_from_items(
                             user.role == 'admin'
                             or file_object.user_id == user.id
                             or await has_access_to_file(file_id, 'read', user)
+                            or ('file', file_id) in folder_items
                         ):
                             if item.get('legacy'):
                                 collection_names.append(f'{file_id}')
@@ -1478,6 +1501,7 @@ async def get_sources_from_items(
                     resource_id=knowledge_base.id,
                     permission='read',
                 )
+                or ('collection', item.get('id')) in folder_items
             ):
                 if (knowledge_base.meta or {}).get('source') == 'external':
                     query_result = await retrieve_external_knowledge(
@@ -1500,6 +1524,7 @@ async def get_sources_from_items(
                                 resource_id=knowledge_base.id,
                                 permission='read',
                             )
+                            or ('collection', item.get('id')) in folder_items
                         ):
                             files = await Knowledges.get_files_by_id(knowledge_base.id)
 
@@ -1570,7 +1595,7 @@ async def get_sources_from_items(
                 continue
 
             # Filter out collections the user cannot read
-            if user:
+            if user and (item.get('type'), item.get('id')) not in folder_items:
                 collection_names = await filter_accessible_collections(collection_names, user)
                 if not collection_names:
                     log.debug(f'access denied for all collections in item {item}')

backend/open_webui/utils/middleware.py

@@ -74,7 +74,6 @@ from open_webui.socket.main import (
     get_event_emitter,
 )
 from open_webui.utils.access_control import has_connection_access, has_permission
-from open_webui.utils.access_control.files import get_accessible_folder_files
 from open_webui.utils.access_control.folders import has_folder_access
 from open_webui.utils.chat import generate_chat_completion
 from open_webui.utils.code_interpreter import execute_code_jupyter
@@ -2363,16 +2362,15 @@ async def process_chat_payload(request, form_data, user, metadata, model):
             if 'system_prompt' in folder.data:
                 form_data = await apply_system_prompt_to_body(folder.data['system_prompt'], form_data, metadata, user)
             if 'files' in folder.data:
-                allowed_files = await get_accessible_folder_files(folder.data['files'], user)
                 if metadata.get('params', {}).get('function_calling') == 'legacy':
                     form_data['files'] = [
-                        *allowed_files,
+                        {'type': 'folder', 'id': folder.id},
                         *form_data.get('files', []),
                     ]
                 else:
                     # Native FC: skip RAG injection, builtin tools
                     # will read folder knowledge from metadata.
-                    metadata['folder_knowledge'] = allowed_files
+                    metadata['folder_knowledge'] = folder.data['files']
 
     # Model "Knowledge" handling
     user_message = get_last_user_message(form_data['messages'])
@@ -2578,23 +2576,6 @@ async def process_chat_payload(request, form_data, user, metadata, model):
     #     urls = extract_urls(prompt)
 
     if files:
-        if not files:
-            files = []
-
-        for file_item in files:
-            if file_item.get('type', 'file') == 'folder':
-                # Get folder files
-                folder_id = file_item.get('id', None)
-                if folder_id:
-                    folder = await Folders.get_folder_by_id(folder_id)
-                    if folder and user.role != 'admin' and not await has_folder_access(
-                        user.id, folder, 'read', db=None
-                    ):
-                        folder = None
-                    if folder and folder.data and 'files' in folder.data:
-                        files = [f for f in files if f.get('id', None) != folder_id]
-                        files = [*files, *await get_accessible_folder_files(folder.data['files'], user)]
-
         # files = [*files, *[{"type": "url", "url": url, "name": url} for url in urls]]
         # Remove duplicate files based on their content
         files = list({json.dumps(f, sort_keys=True): f for f in files}.values())