admin/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix segment deletion race condition (#24408)

Browse Source 
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
This commit is contained in:
kenwoodjw
2025-09-12 15:29:57 +08:00
committed by GitHub
parent 285291f545
commit c91253d05d
3 changed files with 84 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
api/core/rag/index_processor/processor/parent_child_index_processor.py
View File

@@ -113,21 +113,33 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
# node_ids is segment's node_ids
if dataset.indexing_technique == "high_quality":
delete_child_chunks = kwargs.get("delete_child_chunks") or False
precomputed_child_node_ids = kwargs.get("precomputed_child_node_ids")
vector = Vector(dataset)
if node_ids:
child_node_ids = (
db.session.query(ChildChunk.index_node_id)
.join(DocumentSegment, ChildChunk.segment_id == DocumentSegment.id)
.where(
DocumentSegment.dataset_id == dataset.id,
DocumentSegment.index_node_id.in_(node_ids),
ChildChunk.dataset_id == dataset.id,
# Use precomputed child_node_ids if available (to avoid race conditions)
if precomputed_child_node_ids is not None:
child_node_ids = precomputed_child_node_ids
else:
# Fallback to original query (may fail if segments are already deleted)
child_node_ids = (
db.session.query(ChildChunk.index_node_id)
.join(DocumentSegment, ChildChunk.segment_id == DocumentSegment.id)
.where(
DocumentSegment.dataset_id == dataset.id,
DocumentSegment.index_node_id.in_(node_ids),
ChildChunk.dataset_id == dataset.id,
)
.all()
)
.all()
)
child_node_ids = [child_node_id[0] for child_node_id in child_node_ids]
vector.delete_by_ids(child_node_ids)
if delete_child_chunks:
child_node_ids = [child_node_id[0] for child_node_id in child_node_ids if child_node_id[0]]
# Delete from vector index
if child_node_ids:
vector.delete_by_ids(child_node_ids)
# Delete from database
if delete_child_chunks and child_node_ids:
db.session.query(ChildChunk).where(
ChildChunk.dataset_id == dataset.id, ChildChunk.index_node_id.in_(child_node_ids)
).delete(synchronize_session=False)