light worker needs to discover some indexing tasks (#4209)

* light worker needs to discover some indexing tasks

* fix formatting

---------

Co-authored-by: Richard Kuo (Danswer) <rkuo@onyx.app>

backend/onyx/background/celery/apps/light.py

@@ -111,5 +111,6 @@ celery_app.autodiscover_tasks(
         "onyx.background.celery.tasks.vespa",
         "onyx.background.celery.tasks.connector_deletion",
         "onyx.background.celery.tasks.doc_permission_syncing",
+        "onyx.background.celery.tasks.indexing",
     ]
 )

backend/onyx/background/celery/tasks/indexing/tasks.py

@@ -1170,6 +1170,7 @@ def connector_indexing_proxy_task(
     return
 
 
+# primary
 @shared_task(
     name=OnyxCeleryTask.CHECK_FOR_CHECKPOINT_CLEANUP,
     soft_time_limit=300,
@@ -1217,6 +1218,7 @@ def check_for_checkpoint_cleanup(*, tenant_id: str) -> None:
                 )
 
 
+# light worker
 @shared_task(
     name=OnyxCeleryTask.CLEANUP_CHECKPOINT,
     bind=True,

backend/onyx/connectors/confluence/connector.py

@@ -302,7 +302,9 @@ class ConfluenceConnector(
 
             # Create the document
             return Document(
-                id=build_confluence_document_id(self.wiki_base, page["_links"]["webui"], self.is_cloud),
+                id=build_confluence_document_id(
+                    self.wiki_base, page["_links"]["webui"], self.is_cloud
+                ),
                 sections=sections,
                 source=DocumentSource.CONFLUENCE,
                 semantic_identifier=page_title,

backend/tests/daily/connectors/confluence/test_confluence_permissions_basic.py

@@ -45,5 +45,6 @@ def test_confluence_connector_permissions(
     difference = all_full_doc_ids - all_slim_doc_ids
 
     # The set of full doc IDs should be always be a subset of the slim doc IDs
-    assert all_full_doc_ids.issubset(all_slim_doc_ids), \
-        f"Full doc IDs are not a subset of slim doc IDs. Found {len(difference)} IDs in full docs but not in slim docs."
+    assert all_full_doc_ids.issubset(
+        all_slim_doc_ids
+    ), f"Full doc IDs are not a subset of slim doc IDs. Found {len(difference)} IDs in full docs but not in slim docs."