Skip to content

disable all chunks status when disable document #12149

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 27, 2024
Merged

disable all chunks status when disable document #12149

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
26d6bdb
disable all chunks status when disable document
JohnJyong Dec 27, 2024
b8e7a39
update optimized
JohnJyong Dec 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 15 additions & 1 deletion api/tasks/add_document_to_index_task.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,11 @@ def add_document_to_index_task(dataset_document_id: str):
try:
segments = (
db.session.query(DocumentSegment)
.filter(DocumentSegment.document_id == dataset_document.id, DocumentSegment.enabled == True)
.filter(
DocumentSegment.document_id == dataset_document.id,
DocumentSegment.enabled == False,
DocumentSegment.status == "completed",
)
.order_by(DocumentSegment.position.asc())
.all()
)
Expand Down Expand Up @@ -85,6 +89,16 @@ def add_document_to_index_task(dataset_document_id: str):
db.session.query(DatasetAutoDisableLog).filter(
DatasetAutoDisableLog.document_id == dataset_document.id
).delete()

# update segment to enable
db.session.query(DocumentSegment).filter(DocumentSegment.document_id == dataset_document.id).update(
{
DocumentSegment.enabled: True,
DocumentSegment.disabled_at: None,
DocumentSegment.disabled_by: None,
DocumentSegment.updated_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
}
)
db.session.commit()

end_at = time.perf_counter()
Expand Down
11 changes: 11 additions & 0 deletions api/tasks/remove_document_from_index_task.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import datetime
import logging
import time

Expand Down Expand Up @@ -46,6 +47,16 @@ def remove_document_from_index_task(document_id: str):
index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=False)
except Exception:
logging.exception(f"clean dataset {dataset.id} from index failed")
# update segment to disable
db.session.query(DocumentSegment).filter(DocumentSegment.document_id == document.id).update(
{
DocumentSegment.enabled: False,
DocumentSegment.disabled_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
DocumentSegment.disabled_by: document.disabled_by,
DocumentSegment.updated_at: datetime.datetime.now(datetime.UTC).replace(tzinfo=None),
}
)
db.session.commit()

end_at = time.perf_counter()
logging.info(
Expand Down
Loading