refac

Author: tjbck

backend/open_webui/retrieval/utils.py

@@ -932,6 +932,44 @@ def get_reranking_function(reranking_engine, reranking_model, reranking_function
         )
 
 
+async def filter_accessible_collections(
+    collection_names: set[str],
+    user: UserModel,
+    access_type: str = 'read',
+) -> set[str]:
+    """
+    Return only the collection names the user is allowed to access.
+    Admins bypass all checks.  For non-admins:
+      - file-*          → validated via has_access_to_file
+      - user-memory-*   → must match user's own memory collection
+      - knowledge-bases → always denied (meta-collection)
+      - known KB ids    → validated via Knowledges.check_access_by_user_id
+      - everything else → allowed (ephemeral collections like web-search-*)
+    """
+    if user.role == 'admin':
+        return collection_names
+
+    validated = set()
+    for name in collection_names:
+        if name == 'knowledge-bases':
+            continue
+        elif name.startswith('file-'):
+            file_id = name[len('file-'):]
+            if await has_access_to_file(file_id=file_id, access_type=access_type, user=user):
+                validated.add(name)
+        elif name.startswith('user-memory-'):
+            if name == f'user-memory-{user.id}':
+                validated.add(name)
+        else:
+            # May be a knowledge-base ID or an ephemeral collection
+            if await Knowledges.check_access_by_user_id(name, user.id, permission=access_type):
+                validated.add(name)
+            elif not await Knowledges.get_knowledge_by_id(name):
+                # Not a KB at all — ephemeral collection (e.g. web-search-*), allow
+                validated.add(name)
+    return validated
+
+
 async def get_sources_from_items(
     request,
     items,
@@ -1147,6 +1185,13 @@ async def get_sources_from_items(
                 log.debug(f'skipping {item} as it has already been extracted')
                 continue
 
+            # Filter out collections the user cannot read
+            if user:
+                collection_names = await filter_accessible_collections(collection_names, user)
+                if not collection_names:
+                    log.debug(f'access denied for all collections in item {item}')
+                    continue
+
             try:
                 if full_context:
                     # Sync helper makes blocking VECTOR_DB_CLIENT calls;

backend/open_webui/routers/retrieval.py

@@ -82,6 +82,7 @@
 from open_webui.retrieval.web.ydc import search_youcom
 
 from open_webui.retrieval.utils import (
+    filter_accessible_collections,
     get_content_from_url,
     get_embedding_function,
     get_reranking_function,
@@ -2350,50 +2351,19 @@ async def search_query_with_semaphore(query):
 
 async def _validate_collection_access(collection_names: list[str], user, access_type: str = 'read') -> None:
     """
-    Prevent users from accessing collections they don't own.
-    Enforces ownership on user-memory-*, file-*, and knowledge-base collections.
-    Admins bypass this check.
+    Raise 403 if the user lacks access to any of the requested collections.
+    Delegates to the shared filter_accessible_collections utility so the
+    access rules stay in one place.
     """
-    if user.role == 'admin':
-        return
-
-    for name in collection_names:
-        # The 'knowledge-bases' meta-collection stores embedded metadata
-        # (names, descriptions, UUIDs) for every KB in the instance.
-        # Querying it would let any user enumerate all knowledge bases.
-        if name == 'knowledge-bases':
-            raise HTTPException(
-                status_code=status.HTTP_403_FORBIDDEN,
-                detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-            )
-        elif name.startswith('user-memory-') and name != f'user-memory-{user.id}':
-            raise HTTPException(
-                status_code=status.HTTP_403_FORBIDDEN,
-                detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-            )
-        elif name.startswith('file-'):
-            file_id = name[len('file-') :]
-            if not await has_access_to_file(
-                file_id=file_id,
-                access_type=access_type,
-                user=user,
-            ):
-                raise HTTPException(
-                    status_code=status.HTTP_403_FORBIDDEN,
-                    detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-                )
-        else:
-            # Non-prefixed collection names may be knowledge base IDs.
-            # Verify the caller has the required permission on the knowledge base.
-            knowledge = await Knowledges.get_knowledge_by_id(name)
-            if knowledge is not None:
-                if not await Knowledges.check_access_by_user_id(
-                    name, user.id, permission=access_type
-                ):
-                    raise HTTPException(
-                        status_code=status.HTTP_403_FORBIDDEN,
-                        detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-                    )
+    requested = set(collection_names)
+    allowed = await filter_accessible_collections(requested, user, access_type=access_type)
+    denied = requested - allowed
+    if denied:
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
 
 
 class QueryDocForm(BaseModel):