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

fix: fix summary index bug.

Browse Source
This commit is contained in:
FFXN
2026-01-23 13:09:59 +08:00
parent 0769a1c73a
commit 87186b6c73
3 changed files with 9 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
api/tasks/batch_clean_document_task.py
View File

@ -50,7 +50,9 @@ def batch_clean_document_task(document_ids: list[str], dataset_id: str, doc_form
if segments:
index_node_ids = [segment.index_node_id for segment in segments]
index_processor = IndexProcessorFactory(doc_form).init_index_processor()
index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
index_processor.clean(
dataset, index_node_ids, with_keywords=True, delete_child_chunks=True, delete_summaries=True
)
for segment in segments:
image_upload_file_ids = get_image_upload_file_ids(segment.content)

4
api/tasks/clean_document_task.py
View File

@ -51,7 +51,9 @@ def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_i
if segments:
index_node_ids = [segment.index_node_id for segment in segments]
index_processor = IndexProcessorFactory(doc_form).init_index_processor()
index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
index_processor.clean(
dataset, index_node_ids, with_keywords=True, delete_child_chunks=True, delete_summaries=True
)
for segment in segments:
image_upload_file_ids = get_image_upload_file_ids(segment.content)

4
api/tasks/clean_notion_document_task.py
View File

@ -42,7 +42,9 @@ def clean_notion_document_task(document_ids: list[str], dataset_id: str):
).all()
index_node_ids = [segment.index_node_id for segment in segments]
index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
index_processor.clean(
dataset, index_node_ids, with_keywords=True, delete_child_chunks=True, delete_summaries=True
)
segment_ids = [segment.id for segment in segments]
segment_delete_stmt = delete(DocumentSegment).where(DocumentSegment.id.in_(segment_ids))
session.execute(segment_delete_stmt)