feat: add Paperless orphan cleanup endpoint

- POST /maintenance/cleanup/paperless - detect and clean orphaned Paperless documents
- Checks indexed documents against Paperless API
- Removes vectors and graph nodes for deleted documents
- Supports dry_run mode for preview

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2025-12-25 17:00:56 +01:00
co-authored by Claude Opus 4.5
parent 6d5760c297
commit 983a934b85
3 changed files with 188 additions and 1 deletions
+33
View File
@@ -389,6 +389,39 @@ class VectorService:
logger.error(f"Failed to delete chunks for document {document_id}: {e}", exc_info=True)
return 0
async def delete_paperless_document_chunks(
self,
paperless_id: int,
user: str
) -> int:
"""
Delete all chunks for a Paperless document.
Args:
paperless_id: Paperless-ngx document ID
user: User identifier
Returns:
Number of chunks deleted
"""
collection_name = get_qdrant_collection_name(user)
try:
deleted_count = await self.qdrant.delete_by_filter(
collection_name=collection_name,
filter_conditions={
"doc_type": "document",
"paperless_id": paperless_id
}
)
logger.info(f"Deleted chunks for Paperless document {paperless_id}")
return deleted_count
except Exception as e:
logger.error(f"Failed to delete chunks for Paperless document {paperless_id}: {e}", exc_info=True)
return 0
async def delete_collection_chunks(
self,
collection_id: str,