AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-14 10:15:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

ignore errors when creating duplicate indexes (#18069)

Browse Source 
Co-authored-by: 璟义 <yangshangpo.ysp@alibaba-inc.com>
This commit is contained in:
YANG 2025-04-15 15:48:16 +08:00 committed by GitHub
parent 0a9031fd42
commit d119c7d629
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py
View File

@ -139,13 +139,17 @@ class AnalyticdbVectorBySql:
) )
if embedding_dimension is not None: if embedding_dimension is not None:
index_name = f"{self._collection_name}_embedding_idx" index_name = f"{self._collection_name}_embedding_idx"
cur.execute(f"ALTER TABLE {self.table_name} ALTER COLUMN vector SET STORAGE PLAIN") try:
cur.execute( cur.execute(f"ALTER TABLE {self.table_name} ALTER COLUMN vector SET STORAGE PLAIN")
f"CREATE INDEX {index_name} ON {self.table_name} USING ann(vector) " cur.execute(
f"WITH(dim='{embedding_dimension}', distancemeasure='{self.config.metrics}', " f"CREATE INDEX {index_name} ON {self.table_name} USING ann(vector) "
f"pq_enable=0, external_storage=0)" f"WITH(dim='{embedding_dimension}', distancemeasure='{self.config.metrics}', "
) f"pq_enable=0, external_storage=0)"
cur.execute(f"CREATE INDEX ON {self.table_name} USING gin(to_tsvector)") )
cur.execute(f"CREATE INDEX ON {self.table_name} USING gin(to_tsvector)")
except Exception as e:
if "already exists" not in str(e):
raise e
redis_client.set(collection_exist_cache_key, 1, ex=3600) redis_client.set(collection_exist_cache_key, 1, ex=3600)
def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs): def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs):
@ -177,9 +181,11 @@ class AnalyticdbVectorBySql:
return cur.fetchone() is not None return cur.fetchone() is not None
def delete_by_ids(self, ids: list[str]) -> None: def delete_by_ids(self, ids: list[str]) -> None:
if not ids:
return
with self._get_cursor() as cur: with self._get_cursor() as cur:
try: try:
cur.execute(f"DELETE FROM {self.table_name} WHERE ref_doc_id IN %s", (tuple(ids),)) cur.execute(f"DELETE FROM {self.table_name} WHERE ref_doc_id = ANY(%s)", (ids,))
except Exception as e: except Exception as e:
if "does not exist" not in str(e): if "does not exist" not in str(e):
raise e raise e
@ -240,7 +246,7 @@ class AnalyticdbVectorBySql:
ts_rank(to_tsvector, to_tsquery_from_text(%s, 'zh_cn'), 32) AS score ts_rank(to_tsvector, to_tsquery_from_text(%s, 'zh_cn'), 32) AS score
FROM {self.table_name} FROM {self.table_name}
WHERE to_tsvector@@to_tsquery_from_text(%s, 'zh_cn') {where_clause} WHERE to_tsvector@@to_tsquery_from_text(%s, 'zh_cn') {where_clause}
ORDER BY score DESC ORDER BY (score,id) DESC
LIMIT {top_k}""", LIMIT {top_k}""",
(f"'{query}'", f"'{query}'"), (f"'{query}'", f"'{query}'"),
) )