Elasticsearchstore similarity search algorithm

[kaan9700]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from langchain_elasticsearch import ElasticsearchStore

db = ElasticsearchStore(es_url=self.host, index_name=index_name, embedding=embedding,
                                     es_user="",
                                     es_password="")

db.invoke(query)

Description

I am using the ElasticsearchStore to connect to my Elasticsearch (which is running on 8.8.0 on Docker). For a research i need to know which algorithm is used for the similarity search, when calling db.invoke().
Does anyone know that, or has an idea how can i research that?

System Info

System Information

OS: Windows
OS Version: 10.0.22631
Python Version: 3.10.13 | packaged by Anaconda, Inc. | (main, Sep 11 2023, 13:24:38) [MSC v.1916 64 bit (AMD64)]

Package Information

langchain_core: 0.2.22
langchain: 0.2.10
langchain_community: 0.2.9
langsmith: 0.1.85
langchain_elasticsearch: 0.2.2
langchain_experimental: 0.0.62
langchain_openai: 0.1.17
langchain_qdrant: 0.1.3
langchain_text_splitters: 0.2.2

Packages not installed (Not Necessarily a Problem)

The following packages were not found:

langgraph
langserve

[dosubot[bot]]

The algorithm used for the similarity search when calling db.invoke() in the ElasticsearchStore from the langchain_elasticsearch package is the HNSW (Hierarchical Navigable Small World) algorithm ^[1].

To continue talking to Dosu, mention @dosu.