Elasticsearch integrations

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-free JSON documents.

Installation and setup

Setup Elasticsearch

There are two ways to get started with Elasticsearch:

Install Elasticsearch on your local machine

The easiest way to run Elasticsearch locally for development and testing is using the start-local script. This script sets up Elasticsearch using Docker with a simple one-line command.

curl -fsSL https://elastic.co/start-local | sh

This creates an elastic-start-local folder. To start Elasticsearch:

cd elastic-start-local
./start.sh

Elasticsearch will be available at http://localhost:9200. The password for the elastic user and API key are automatically generated and stored in the .env file in the elastic-start-local folder.

If you only need Elasticsearch without Kibana, you can use the --esonly option:

curl -fsSL https://elastic.co/start-local | sh -s -- --esonly

Deploy Elasticsearch on elastic cloud

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

Install client

pip install elasticsearch
pip install langchain-elasticsearch

uv add elasticsearch
uv add langchain-elasticsearch

Embedding models

See a usage example.

from langchain_elasticsearch import ElasticsearchEmbeddings

Vector store

See a usage example.

from langchain_elasticsearch import ElasticsearchStore

Retrievers

ElasticsearchRetriever

The ElasticsearchRetriever enables flexible access to all Elasticsearch features through the Query DSL.

See a usage example.

from langchain_elasticsearch import ElasticsearchRetriever

LLM cache

from langchain_elasticsearch import ElasticsearchCache

Byte store

See a usage example.

from langchain_elasticsearch import ElasticsearchEmbeddingsCache

Chain

It is a chain for interacting with Elasticsearch Database.

from langchain_classic.chains.elasticsearch_database import ElasticsearchDatabaseChain