youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-03 08:58:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

perf: use batch delete method instead of single delete (#32036)

Browse Source 
Co-authored-by: fatelei <fatelei@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: FFXN <lizy@dify.ai>
This commit is contained in:
QuantumGhost
2026-02-06 15:12:32 +08:00
committed by NFish
parent 9898df5ed5
commit b035b091fa
4 changed files with 190 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
api/tasks/delete_segment_from_index_task.py
View File

@ -3,6 +3,7 @@ import time
import click
from celery import shared_task
from sqlalchemy import delete
from core.db.session_factory import session_factory
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
@ -67,8 +68,14 @@ def delete_segment_from_index_task(
if segment_attachment_bindings:
attachment_ids = [binding.attachment_id for binding in segment_attachment_bindings]
index_processor.clean(dataset=dataset, node_ids=attachment_ids, with_keywords=False)
for binding in segment_attachment_bindings:
session.delete(binding)
segment_attachment_bind_ids = [i.id for i in segment_attachment_bindings]
for i in range(0, len(segment_attachment_bind_ids), 1000):
segment_attachment_bind_delete_stmt = delete(SegmentAttachmentBinding).where(
SegmentAttachmentBinding.id.in_(segment_attachment_bind_ids[i : i + 1000])
)
session.execute(segment_attachment_bind_delete_stmt)
# delete upload file
session.query(UploadFile).where(UploadFile.id.in_(attachment_ids)).delete(synchronize_session=False)
session.commit()