Skip to main content


This template performs RAG with Lantern.

Lantern is an open-source vector database built on top of PostgreSQL. It enables vector search and embedding generation inside your database.

Environment Setup​

Set the OPENAI_API_KEY environment variable to access the OpenAI models.

To get your OPENAI_API_KEY, navigate to API keys on your OpenAI account and create a new secret key.

To find your LANTERN_URL and LANTERN_SERVICE_KEY, head to your Lantern project's API settings.

  • LANTERN_URL corresponds to the Project URL
  • LANTERN_SERVICE_KEY corresponds to the service_role API key

Setup Lantern Database​

Use these steps to setup your Lantern database if you haven't already.

  1. Head to to create your Lantern database.

  2. In your favorite SQL client, jump to the SQL editor and run the following script to setup your database as a vector store:

    -- Create a table to store your documents
    create table
    documents (
    id uuid primary key,
    content text, -- corresponds to Document.pageContent
    metadata jsonb, -- corresponds to Document.metadata
    embedding REAL[1536] -- 1536 works for OpenAI embeddings, change as needed

    -- Create a function to search for documents
    create function match_documents (
    query_embedding REAL[1536],
    filter jsonb default '{}'
    ) returns table (
    id uuid,
    content text,
    metadata jsonb,
    similarity float
    ) language plpgsql as $$
    #variable_conflict use_column
    return query
    1 - (documents.embedding <=> query_embedding) as similarity
    from documents
    where metadata @> filter
    order by documents.embedding <=> query_embedding;

Setup Environment Variables​

Since we are using Lantern and OpenAIEmbeddings, we need to load their API keys.


First, install the LangChain CLI:

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-lantern

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

langchain app add rag-lantern

And add the following code to your file:

from rag_lantern.chain import chain as rag_lantern_chain

add_routes(app, rag_lantern_chain, path="/rag-lantern")

(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-lantern")

Was this page helpful?

You can leave detailed feedback on GitHub.