enh: files data controls

backend/open_webui/models/files.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from sqlalchemy.orm import Session
 from open_webui.internal.db import Base, JSONField, get_db, get_db_context
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, model_validator
 from sqlalchemy import BigInteger, Column, String, Text, JSON
 
 log = logging.getLogger(__name__)
@@ -63,6 +63,25 @@ class FileMeta(BaseModel):
 
     model_config = ConfigDict(extra="allow")
 
+    @model_validator(mode="before")
+    @classmethod
+    def sanitize_meta(cls, data):
+        """Sanitize metadata fields to handle malformed legacy data."""
+        if not isinstance(data, dict):
+            return data
+        
+        # Handle content_type that may be a list like ['application/pdf', None]
+        content_type = data.get("content_type")
+        if isinstance(content_type, list):
+            # Extract first non-None string value
+            data["content_type"] = next(
+                (item for item in content_type if isinstance(item, str)), None
+            )
+        elif content_type is not None and not isinstance(content_type, str):
+            data["content_type"] = None
+        
+        return data
+
 
 class FileModelResponse(BaseModel):
     id: str
@@ -74,7 +93,7 @@ class FileModelResponse(BaseModel):
     meta: FileMeta
 
     created_at: int  # timestamp in epoch
-    updated_at: int  # timestamp in epoch
+    updated_at: Optional[int] = None  # timestamp in epoch, optional for legacy files
 
     model_config = ConfigDict(extra="allow")
 

backend/open_webui/routers/files.py

@@ -282,7 +282,7 @@ def upload_file_handler(
                     },
                     "meta": {
                         "name": name,
-                        "content_type": file.content_type,
+                        "content_type": file.content_type if isinstance(file.content_type, str) else None,
                         "size": len(contents),
                         "data": file_metadata,
                     },
@@ -827,6 +827,23 @@ async def delete_file_by_id(
         or has_access_to_file(id, "write", user, db=db)
     ):
 
+        # Clean up KB associations and embeddings before deleting
+        knowledges = Knowledges.get_knowledges_by_file_id(id, db=db)
+        for knowledge in knowledges:
+            # Remove KB-file relationship
+            Knowledges.remove_file_from_knowledge_by_id(knowledge.id, id, db=db)
+            # Clean KB embeddings (same logic as /knowledge/{id}/file/remove)
+            try:
+                VECTOR_DB_CLIENT.delete(
+                    collection_name=knowledge.id, filter={"file_id": id}
+                )
+                if file.hash:
+                    VECTOR_DB_CLIENT.delete(
+                        collection_name=knowledge.id, filter={"hash": file.hash}
+                    )
+            except Exception as e:
+                log.debug(f"KB embedding cleanup for {knowledge.id}: {e}")
+
         result = Files.delete_file_by_id(id, db=db)
         if result:
             try: