Skip to content

fix: use simple config for SearchVector to avoid double stemming #6225

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
zhanweizhang7 merged 1 commit into from
Jun 15, 2026
Merged

fix: use simple config for SearchVector to avoid double stemming #6225

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion apps/common/event/listener_manage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,7 +230,7 @@ def tokenize_by_paragraph(paragraph_id):
)
data_list = list(QuerySet(Embedding).filter(paragraph_id=paragraph_id))
for data, chunk in zip(data_list, chunks):
data.search_vector = SearchVector(Value(to_ts_vector(chunk, user_words=user_words)))
data.search_vector = SearchVector(Value(to_ts_vector(chunk, user_words=user_words)), config='simple')
# 批量保存，减少数据库写入次数
QuerySet(Embedding).filter(paragraph_id=paragraph_id).bulk_update(data_list, ["search_vector"])

Expand Down
5 changes: 3 additions & 2 deletions apps/knowledge/vector/pg_vector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ def _save(
source_id=source_id,
embedding=text_embedding,
source_type=source_type,
search_vector=SearchVector(Value(to_ts_vector(text, user_words=terms))),
search_vector=SearchVector(Value(to_ts_vector(text, user_words=terms)), config='simple'),
)
embedding.save()
return True
Expand Down Expand Up @@ -99,7 +99,8 @@ def _batch_save(self, text_list: List[Dict], embedding: Embeddings, is_the_task_
.values_list("content", flat=True)
),
)
)
),
config='simple',
),
)
for index in range(0, len(texts))
Expand Down
Loading