Skip to main content


This template performs RAG using Elasticsearch.

It relies on sentence transformer MiniLM-L6-v2 for embedding passages and questions.

Environment Setup​

Set the OPENAI_API_KEY environment variable to access the OpenAI models.

To connect to your Elasticsearch instance, use the following environment variables:


For local development with Docker, use:

export ES_URL="http://localhost:9200"

And run an Elasticsearch instance in Docker with

docker run -p 9200:9200 -e "discovery.type=single-node" -e "" -e ""


To use this package, you should first have the LangChain CLI installed:

pip install -U langchain-cli

To create a new LangChain project and install this as the only package, you can do:

langchain app new my-app --package rag-elasticsearch

If you want to add this to an existing project, you can just run:

langchain app add rag-elasticsearch

And add the following code to your file:

from rag_elasticsearch import chain as rag_elasticsearch_chain

add_routes(app, rag_elasticsearch_chain, path="/rag-elasticsearch")

(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. You can sign up for LangSmith here. If you don't have access, you can skip this section

export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"

If you are inside this directory, then you can spin up a LangServe instance directly by:

langchain serve

This will start the FastAPI app with a server is running locally at http://localhost:8000

We can see all templates at We can access the playground at

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/rag-elasticsearch")

For loading the fictional workplace documents, run the following command from the root of this repository:


However, you can choose from a large number of document loaders here.

Was this page helpful?

You can also leave detailed feedback on GitHub.