Merge remote-tracking branch 'origin/main' into feat/new-onboarding

src/main.py

@@ -335,32 +335,13 @@ async def _ingest_default_documents_langflow(services, file_paths):
     """Ingest default documents using Langflow upload-ingest-delete pipeline."""
     langflow_file_service = services["langflow_file_service"]
     session_manager = services["session_manager"]
+    task_service = services["task_service"]
 
     logger.info(
         "Using Langflow ingestion pipeline for default documents",
         file_count=len(file_paths),
     )
 
-    success_count = 0
-    error_count = 0
-
-    for file_path in file_paths:
-        try:
-            logger.debug("Processing file with Langflow pipeline", file_path=file_path)
-
-            # Read file content
-            with open(file_path, "rb") as f:
-                content = f.read()
-
-            # Create file tuple for upload
-            filename = os.path.basename(file_path)
-            # Determine content type based on file extension
-            content_type, _ = mimetypes.guess_type(filename)
-            if not content_type:
-                content_type = "application/octet-stream"
-
-            file_tuple = (filename, content, content_type)
-
     # Use AnonymousUser details for default documents
     from session_manager import AnonymousUser
 
@@ -392,40 +373,26 @@ async def _ingest_default_documents_langflow(services, file_paths):
         }
     }
 
-            # Use langflow upload_and_ingest_file method with JWT token
+    # Create a langflow upload task for trackable progress
-            result = await langflow_file_service.upload_and_ingest_file(
+    task_id = await task_service.create_langflow_upload_task(
-                file_tuple=file_tuple,
+        user_id=None,  # Anonymous user
-                session_id=None,  # No session for default documents
+        file_paths=file_paths,
-                tweaks=default_tweaks,  # Add anonymous user metadata
+        langflow_file_service=langflow_file_service,
-                settings=None,  # Use default ingestion settings
+        session_manager=session_manager,
-                jwt_token=effective_jwt,  # Use JWT token (anonymous if needed)
+        jwt_token=effective_jwt,
-                delete_after_ingest=True,  # Clean up after ingestion
-                owner=None,
         owner_name=anonymous_user.name,
         owner_email=anonymous_user.email,
-                connector_type="system_default",
+        session_id=None,  # No session for default documents
+        tweaks=default_tweaks,
+        settings=None,  # Use default ingestion settings
+        delete_after_ingest=True,  # Clean up after ingestion
+        replace_duplicates=False,
     )
 
     logger.info(
-                "Successfully ingested file via Langflow",
+        "Started Langflow ingestion task for default documents",
-                file_path=file_path,
+        task_id=task_id,
-                result_status=result.get("status"),
+        file_count=len(file_paths),
-            )
-            success_count += 1
-
-        except Exception as e:
-            logger.error(
-                "Failed to ingest file via Langflow",
-                file_path=file_path,
-                error=str(e),
-            )
-            error_count += 1
-
-    logger.info(
-        "Langflow ingestion completed",
-        success_count=success_count,
-        error_count=error_count,
-        total_files=len(file_paths),
     )