github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-05-31 12:09:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Improvement: Allow passing parameters to the underlying es_client. Closes: #14403 (#14435)

Browse Source 
### Description

In https://github.com/langchain-ai/langchain/issues/14403, the user
mentioned that he hopes not to verify ssl and needs to pass more
parameters

I found that the `Elasticsearch` class [has very many
parameters](98f2af2134/elasticsearch/_sync/client/__init__.py (L131-L191)
):

<img width="1097" alt="Screenshot 2023-12-08 at 4 24 39 PM"
src="https://github.com/langchain-ai/langchain/assets/10000925/f2201554-b41a-4388-a8e8-c14a2d0466d4">

In order to adapt to more situations, I want to add the kwargs parameter
so that users can enter more `Elasticsearch` parameters. Like
[redis](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/vectorstores/redis/base.py#L253),
[tair](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/vectorstores/tair.py#L32),
[myscale](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/vectorstores/myscale.py#L112)
and so on.
This commit is contained in:
Bob Lin 2024-01-02 18:48:17 -06:00 committed by GitHub
parent 8aa921d3a4
commit e93be14c11
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 1 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

@ -256,7 +256,7 @@ class ExactRetrievalStrategy(BaseRetrievalStrategy):
elif similarity is DistanceStrategy.DOT_PRODUCT:
similarityAlgo = f"""
double value = dotProduct(params.query_vector, '{vector_query_field}');
return sigmoid(1, Math.E, -value);
return sigmoid(1, Math.E, -value);
"""
else:
raise ValueError(f"Similarity {similarity} not supported.")
@ -512,6 +512,7 @@ class ElasticsearchStore(VectorStore):
]
] = None,
strategy: BaseRetrievalStrategy = ApproxRetrievalStrategy(),
es_params: Optional[Dict[str, Any]] = None,
):
self.embedding = embedding
self.index_name = index_name
@ -535,6 +536,7 @@ class ElasticsearchStore(VectorStore):
password=es_password,
cloud_id=es_cloud_id,
api_key=es_api_key,
es_params=es_params,
)
else:
raise ValueError(
@ -556,6 +558,7 @@ class ElasticsearchStore(VectorStore):
api_key: Optional[str] = None,
username: Optional[str] = None,
password: Optional[str] = None,
es_params: Optional[Dict[str, Any]] = None,
) -> "Elasticsearch":
try:
import elasticsearch
@ -584,6 +587,9 @@ class ElasticsearchStore(VectorStore):
elif username and password:
connection_params["basic_auth"] = (username, password)
if es_params is not None:
connection_params.update(es_params)
es_client = elasticsearch.Elasticsearch(
**connection_params,
headers={"user-agent": ElasticsearchStore.get_user_agent()},