highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-09-27 20:38:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix sync to use update_single (#2822)

Browse Source
This commit is contained in:
rkuo-danswer
2024-10-17 12:43:34 -07:00
committed by GitHub
parent 389c7b72db
commit 114326d11a
2 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/danswer/background/celery/tasks/shared/tasks.py
View File

@@ -111,7 +111,7 @@ def document_by_cc_pair_cleanup_task(
pass pass
task_logger.info( task_logger.info(
f"document_id={document_id} refcount={count} action={action} chunks={chunks_affected}" f"document_id={document_id} action={action} refcount={count} chunks={chunks_affected}"
) )
db_session.commit() db_session.commit()
except SoftTimeLimitExceeded: except SoftTimeLimitExceeded:

14
backend/danswer/background/celery/tasks/vespa/tasks.py
View File

@@ -45,7 +45,7 @@ from danswer.db.models import DocumentSet
from danswer.db.models import UserGroup from danswer.db.models import UserGroup
from danswer.document_index.document_index_utils import get_both_index_names from danswer.document_index.document_index_utils import get_both_index_names
from danswer.document_index.factory import get_default_document_index from danswer.document_index.factory import get_default_document_index
from danswer.document_index.interfaces import UpdateRequest from danswer.document_index.interfaces import VespaDocumentFields
from danswer.redis.redis_pool import get_redis_client from danswer.redis.redis_pool import get_redis_client
from danswer.utils.variable_functionality import fetch_versioned_implementation from danswer.utils.variable_functionality import fetch_versioned_implementation
from danswer.utils.variable_functionality import ( from danswer.utils.variable_functionality import (
@@ -609,20 +609,24 @@ def vespa_metadata_sync_task(
doc_access = get_access_for_document( doc_access = get_access_for_document(
document_id=document_id, db_session=db_session document_id=document_id, db_session=db_session
) )
update_request = UpdateRequest(
document_ids=[document_id], fields = VespaDocumentFields(
document_sets=update_doc_sets, document_sets=update_doc_sets,
access=doc_access, access=doc_access,
boost=doc.boost, boost=doc.boost,
hidden=doc.hidden, hidden=doc.hidden,
) )
# update Vespa # update Vespa. OK if doc doesn't exist. Raises exception otherwise.
document_index.update(update_requests=[update_request]) chunks_affected = document_index.update_single(document_id, fields=fields)
# update db last. Worst case = we crash right before this and # update db last. Worst case = we crash right before this and
# the sync might repeat again later # the sync might repeat again later
mark_document_as_synced(document_id, db_session) mark_document_as_synced(document_id, db_session)
task_logger.info(
f"document_id={document_id} action=sync chunks={chunks_affected}"
)
except SoftTimeLimitExceeded: except SoftTimeLimitExceeded:
task_logger.info(f"SoftTimeLimitExceeded exception. doc_id={document_id}") task_logger.info(f"SoftTimeLimitExceeded exception. doc_id={document_id}")
except Exception as e: except Exception as e: