Skip to main content
Aerospike Vector is now live with LangChain integrationTell me more
Loading

Create a RAG application using LangChain

Overview​

This guide describes how to create an example Retrieval Augmented Generation (RAG) application using LangChain templates.

Prerequisites​

You need the following components to set up this application:

Install the LangChain CLI​

Run the following to install the LangChain CLI, which gives you access to a set of templates for building applications:

pip install -U langchain-cli

Generate an application​

Run the following to create the necessary Python files and install dependencies:

langchain app new my-app

Apply the Aerospike RAG template​

Run the following in your my-app application folder to apply the Aerospike RAG application template:

langchain app add --repo="aerospike/rag-aerospike/" --branch="main"

Add route details for your application​

Make the following changes to app/server.py to set the route for the RAG application:

  1. Add the following to your import:

    from rag_aerospike import chain as rag_aerospike_chain

  2. Replace add_routes(app, NotImplemented) with the following:

    add_routes(app, rag_aerospike_chain, path="/rag-aerospike")

Set required environment variables​

Run the following to export your OpenAI API key and any other relevant environment variables:

export OPENAI_API_KEY=<your-OpenAI-api-key>
export AVS_HOST=<your-AVS-host> #default localhost
export AVS_PORT=<your-AVS-port> #default 5000
export AVS_NAMESPACE=<your-AVS-namespace> #default test
export DATASOURCE=<your-datasource-url> #default https://aerospike.com/files/ebooks/aerospike-up-and-running-early-release3.pdf

Set up LangSmith (optional)​

Set your LangChain credentials if you want to enable full application monitoring — this requires a paid account on langchain.com.

export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"

Serve the application​

Run the following to start serving the application:

langchain serve

It will take some time to tokenize and embed your datasource. When finished, you should see the following log line:

INFO:     Application startup complete.

Test your application​

When your application is serving, navigate to http://localhost:8000/rag-aerospike/playground/ and ask a context-relevant question.

image