Skip to content

fix(knowledge): create HNSW index with IF NOT EXISTS #7692

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

Closed
ump45nose wants to merge 1 commit into from
Closed

fix(knowledge): create HNSW index with IF NOT EXISTS #7692

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
7 changes: 5 additions & 2 deletions apps/knowledge/serializers/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,9 +269,12 @@ def create_knowledge_index(knowledge_id=None, document_id=None):
dims = result[0]['dims']
# 超过2000维度不创建索引，pgvector hnsw索引不支持超过2000维度
if dims < 2000:
sql = f"""CREATE INDEX "embedding_hnsw_idx_{k_id}" ON embedding USING hnsw ((embedding::vector({dims})) vector_cosine_ops) WHERE knowledge_id = '{k_id}'"""
# IF NOT EXISTS: parallel document embedding tasks for the same
# knowledge base can all pass the pg_indexes check above, then race
# on CREATE INDEX (DuplicateTable). Treat a concurrent create as OK.
sql = f"""CREATE INDEX IF NOT EXISTS "embedding_hnsw_idx_{k_id}" ON embedding USING hnsw ((embedding::vector({dims})) vector_cosine_ops) WHERE knowledge_id = '{k_id}'"""
update_execute(sql, [])
maxkb_logger.info(f'Created index for knowledge ID: {k_id}')
maxkb_logger.info(f'Ensured index for knowledge ID: {k_id}')


def drop_knowledge_index(knowledge_id=None, document_id=None):
Expand Down
Loading