github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-15 06:26:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

tair fix distance_type error, and add hybrid search (#9531)

Browse Source 
- fix: distance_type error, 
- feature: Tair add hybrid search

---------

Co-authored-by: thw <hanwen.thw@alibaba-inc.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit is contained in:
Keras Conv3d
2023-08-24 07:38:31 +08:00
committed by GitHub
parent cd81e8a8f2
commit cbaea8d63b
2 changed files with 99 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
libs/langchain/langchain/vectorstores/tair.py
View File

@@ -86,6 +86,10 @@ class Tair(VectorStore):
"""Add texts data to an existing index."""
ids = []
keys = kwargs.get("keys", None)
use_hybrid_search = False
index = self.client.tvs_get_index(self.index_name)
if index is not None and index.get("lexical_algorithm") == "bm25":
use_hybrid_search = True
# Write data to tair
pipeline = self.client.pipeline(transaction=False)
embeddings = self.embedding_function.embed_documents(list(texts))
@@ -93,16 +97,30 @@ class Tair(VectorStore):
# Use provided key otherwise use default key
key = keys[i] if keys else _uuid_key()
metadata = metadatas[i] if metadatas else {}
pipeline.tvs_hset(
self.index_name,
key,
embeddings[i],
False,
**{
self.content_key: text,
self.metadata_key: json.dumps(metadata),
},
)
if use_hybrid_search:
# tair use TEXT attr hybrid search
pipeline.tvs_hset(
self.index_name,
key,
embeddings[i],
False,
**{
"TEXT": text,
self.content_key: text,
self.metadata_key: json.dumps(metadata),
},
)
else:
pipeline.tvs_hset(
self.index_name,
key,
embeddings[i],
False,
**{
self.content_key: text,
self.metadata_key: json.dumps(metadata),
},
)
ids.append(key)
pipeline.execute()
return ids
@@ -166,7 +184,7 @@ class Tair(VectorStore):
distance_type = tairvector.DistanceMetric.InnerProduct
if "distance_type" in kwargs:
distance_type = kwargs.pop("distance_typ")
distance_type = kwargs.pop("distance_type")
index_type = tairvector.IndexType.HNSW
if "index_type" in kwargs:
index_type = kwargs.pop("index_type")