mirror of
https://github.com/langgenius/dify.git
synced 2026-05-01 07:58:02 +08:00
Plugin/merge main to plugin/beta 20250122 (#12962)
Signed-off-by: yihong0618 <zouzou0208@gmail.com> Signed-off-by: -LAN- <laipz8200@outlook.com> Co-authored-by: kurokobo <kuro664@gmail.com> Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com> Co-authored-by: NFish <douxc512@gmail.com> Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com> Co-authored-by: eux <euxuuu@gmail.com> Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com> Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com> Co-authored-by: lotsik <lotsik@mail.ru> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com> Co-authored-by: nite-knite <nkCoding@gmail.com> Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com> Co-authored-by: CN-P5 <heibai2006@gmail.com> Co-authored-by: CN-P5 <heibai2006@qq.com> Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com> Co-authored-by: yihong <zouzou0208@gmail.com> Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com> Co-authored-by: -LAN- <laipz8200@outlook.com> Co-authored-by: Boris Feld <lothiraldan@gmail.com> Co-authored-by: mbo <himabo@gmail.com> Co-authored-by: mabo <mabo@aeyes.ai> Co-authored-by: Warren Chen <warren.chen830@gmail.com> Co-authored-by: KVOJJJin <jzongcode@gmail.com> Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com> Co-authored-by: jiandanfeng <chenjh3@wangsu.com> Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com> Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com> Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com> Co-authored-by: Xu Song <xusong.vip@gmail.com> Co-authored-by: rayshaw001 <396301947@163.com> Co-authored-by: Ding Jiatong <dingjiatong@gmail.com> Co-authored-by: Bowen Liang <liangbowen@gf.com.cn> Co-authored-by: JasonVV <jasonwangiii@outlook.com> Co-authored-by: le0zh <newlight@qq.com> Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com> Co-authored-by: k-zaku <zaku99@outlook.jp> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: luckylhb90 <luckylhb90@gmail.com> Co-authored-by: hobo.l <hobo.l@binance.com> Co-authored-by: jiangbo721 <365065261@qq.com> Co-authored-by: 刘江波 <jiangbo721@163.com> Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com> Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com> Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: zxhlyh <jasonapring2015@outlook.com> Co-authored-by: sino <sino2322@gmail.com> Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com> Co-authored-by: lowell <lowell.hu@zkteco.in>
This commit is contained in:
@ -258,7 +258,7 @@ class LindormVectorStore(BaseVector):
|
||||
hnsw_ef_construction = kwargs.pop("hnsw_ef_construction", 500)
|
||||
ivfpq_m = kwargs.pop("ivfpq_m", dimension)
|
||||
nlist = kwargs.pop("nlist", 1000)
|
||||
centroids_use_hnsw = kwargs.pop("centroids_use_hnsw", True if nlist >= 5000 else False)
|
||||
centroids_use_hnsw = kwargs.pop("centroids_use_hnsw", nlist >= 5000)
|
||||
centroids_hnsw_m = kwargs.pop("centroids_hnsw_m", 24)
|
||||
centroids_hnsw_ef_construct = kwargs.pop("centroids_hnsw_ef_construct", 500)
|
||||
centroids_hnsw_ef_search = kwargs.pop("centroids_hnsw_ef_search", 100)
|
||||
@ -305,7 +305,7 @@ def default_text_mapping(dimension: int, method_name: str, **kwargs: Any) -> dic
|
||||
if method_name == "ivfpq":
|
||||
ivfpq_m = kwargs["ivfpq_m"]
|
||||
nlist = kwargs["nlist"]
|
||||
centroids_use_hnsw = True if nlist > 10000 else False
|
||||
centroids_use_hnsw = nlist > 10000
|
||||
centroids_hnsw_m = 24
|
||||
centroids_hnsw_ef_construct = 500
|
||||
centroids_hnsw_ef_search = 100
|
||||
|
||||
@ -57,6 +57,11 @@ CREATE TABLE IF NOT EXISTS {table_name} (
|
||||
) using heap;
|
||||
"""
|
||||
|
||||
SQL_CREATE_INDEX = """
|
||||
CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name}
|
||||
USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64);
|
||||
"""
|
||||
|
||||
|
||||
class PGVector(BaseVector):
|
||||
def __init__(self, collection_name: str, config: PGVectorConfig):
|
||||
@ -205,7 +210,10 @@ class PGVector(BaseVector):
|
||||
with self._get_cursor() as cur:
|
||||
cur.execute("CREATE EXTENSION IF NOT EXISTS vector")
|
||||
cur.execute(SQL_CREATE_TABLE.format(table_name=self.table_name, dimension=dimension))
|
||||
# TODO: create index https://github.com/pgvector/pgvector?tab=readme-ov-file#indexing
|
||||
# PG hnsw index only support 2000 dimension or less
|
||||
# ref: https://github.com/pgvector/pgvector?tab=readme-ov-file#indexing
|
||||
if dimension <= 2000:
|
||||
cur.execute(SQL_CREATE_INDEX.format(table_name=self.table_name))
|
||||
redis_client.set(collection_exist_cache_key, 1, ex=3600)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user