Fix one data source can be synced to multiple dataset (#16023)

Fix one data source can be synced to multiple dataset
Test add/delete - worked.
This commit is contained in:
Wang Qi
2026-06-15 16:54:25 +08:00
committed by GitHub
parent fa6d29603a
commit f6a2075ad0
4 changed files with 106 additions and 5 deletions

View File

@@ -171,7 +171,7 @@ class ConnectorService(CommonService):
return 0, []
source_type = f"{conn.source}/{conn.id}"
retain_doc_ids = {hash128(f"{connector_id}:{file.id}") for file in file_list}
retain_doc_ids = {doc_id for file in file_list for doc_id in (hash128(f"{connector_id}:{file.id}"), hash128(f"{kb_id}:{connector_id}:{file.id}"))}
existing_docs = DocumentService.list_doc_headers_by_kb_and_source_type(
kb_id,
source_type,