Elasticsearch is a distributed, RESTful search and analytics engine.It provides a distributed, multi-tenant-capable full-text search engine with an HTTP web interface and schema-freeJSON documents.

Installation and Setup​

Setup Elasticsearch​

There are two ways to get started with Elasticsearch:

Install Elasticsearch on your local machine via Docker​

Example: Run a single-node Elasticsearch instance with security disabled.This is not recommended for production use.

    docker run -p 9200:9200 -e "discovery.type=single-node" -e "xpack.security.enabled=false" -e "xpack.security.http.ssl.enabled=false" docker.elastic.co/elasticsearch/elasticsearch:8.9.0

Deploy Elasticsearch on Elastic Cloud​

Elastic Cloud is a managed Elasticsearch service. Signup for afree trial.

Install Client​

pip install elasticsearch
pip install langchain-elasticsearch

Embedding models​

See ausage example.

from langchain_elasticsearchimport ElasticsearchEmbeddings

Vector store​

See ausage example.

from langchain_elasticsearchimport ElasticsearchStore

Third-party integrations​

EcloudESVectorStore​

from langchain_community.vectorstores.ecloud_vector_searchimport EcloudESVectorStore

Retrievers​

ElasticsearchRetriever​

TheElasticsearchRetriever enables flexible access to all Elasticsearch featuresthrough the Query DSL.

See ausage example.

from langchain_elasticsearchimport ElasticsearchRetriever

BM25​

See ausage example.

from langchain_community.retrieversimport ElasticSearchBM25Retriever

Memory​

See ausage example.

from langchain_elasticsearchimport ElasticsearchChatMessageHistory

LLM cache​

See ausage example.

from langchain_elasticsearchimport ElasticsearchCache

Byte Store​

See ausage example.

from langchain_elasticsearchimport ElasticsearchEmbeddingsCache

Chain​

It is a chain for interacting with Elasticsearch Database.

from langchain.chains.elasticsearch_databaseimport ElasticsearchDatabaseChain