github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-21 22:29:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: ElasticsearchStore enable max inner product (#16393)

Browse Source 
Enable max inner product for approximate retrieval strategy. For exact
strategy we lack the necessary `maxInnerProduct` function in the
Painless scripting language, this is why we do not add it there.

Similarity docs:
https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Joe McElroy <joseph.mcelroy@elastic.co>
This commit is contained in:
Max Jakob 2024-01-22 20:26:18 +01:00 committed by GitHub
parent fc196cab12
commit 8569b8f680
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
libs/community/langchain_community/vectorstores/elasticsearch.py
View File

@ -214,6 +214,8 @@ class ApproxRetrievalStrategy(BaseRetrievalStrategy):
similarityAlgo = "l2_norm"
elif similarity is DistanceStrategy.DOT_PRODUCT:
similarityAlgo = "dot_product"
elif similarity is DistanceStrategy.MAX_INNER_PRODUCT:
similarityAlgo = "max_inner_product"
else:
raise ValueError(f"Similarity {similarity} not supported.")
@ -412,7 +414,7 @@ class ElasticsearchStore(VectorStore):
distance_strategy: Optional. Distance strategy to use when
searching the index.
Defaults to COSINE. Can be one of COSINE,
EUCLIDEAN_DISTANCE, or DOT_PRODUCT.
EUCLIDEAN_DISTANCE, MAX_INNER_PRODUCT or DOT_PRODUCT.
If you want to use a cloud hosted Elasticsearch instance, you can pass in the
cloud_id argument instead of the es_url argument.
@ -508,6 +510,7 @@ class ElasticsearchStore(VectorStore):
DistanceStrategy.COSINE,
DistanceStrategy.DOT_PRODUCT,
DistanceStrategy.EUCLIDEAN_DISTANCE,
DistanceStrategy.MAX_INNER_PRODUCT,
]
] = None,
strategy: BaseRetrievalStrategy = ApproxRetrievalStrategy(),
@ -1128,7 +1131,8 @@ class ElasticsearchStore(VectorStore):
distance_strategy: Optional. Name of the distance
strategy to use. Defaults to "COSINE".
can be one of "COSINE",
"EUCLIDEAN_DISTANCE", "DOT_PRODUCT".
"EUCLIDEAN_DISTANCE", "DOT_PRODUCT",
"MAX_INNER_PRODUCT".
bulk_kwargs: Optional. Additional arguments to pass to
Elasticsearch bulk.
"""