AsyncElasticsearchCache

Setup:

Install langchain_elasticsearch and start Elasticsearch locally using the start-local script.

pip install -qU langchain_elasticsearch
curl -fsSL https://elastic.co/start-local | sh

This will create an elastic-start-local folder. To start Elasticsearch and Kibana:

cd elastic-start-local
./start.sh

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

Initialize the Elasticsearch cache store.

Instantiate:

from langchain_elasticsearch import ElasticsearchCache

cache = ElasticsearchCache(
    index_name="llm-cache",
    es_url="http://localhost:9200"
)

Instantiate with API key:

from langchain_elasticsearch import ElasticsearchCache

cache = ElasticsearchCache(
    index_name="llm-cache",
    es_url="http://localhost:9200",
    es_api_key="your-api-key"
)

Instantiate from cloud:

from langchain_elasticsearch import ElasticsearchCache

cache = ElasticsearchCache(
    index_name="llm-cache",
    es_cloud_id="<cloud_id>",
    es_api_key="your-api-key"
)

Instantiate from existing connection:

from langchain_elasticsearch import ElasticsearchCache
from elasticsearch import Elasticsearch

client = Elasticsearch("http://localhost:9200")
cache = ElasticsearchCache(
    index_name="llm-cache",
    client=client
)

Use with LangChain:

from langchain.globals import set_llm_cache
from langchain_elasticsearch import ElasticsearchCache

set_llm_cache(ElasticsearchCache(
    index_name="llm-cache",
    es_url="http://localhost:9200"
))

For synchronous applications, use the ElasticsearchCache class. For asynchronous applications, use the AsyncElasticsearchCache class.