Build and Deploy a RAG Chatbot with JavaScript, LangChain.js, Next.js, Vercel, OpenAI
freeCodeCamp.org
Ania Kubów builds a chatbot that answers questions about Formula 1 using retrieval-augmented generation (RAG). The data is stored as vector embeddings in a DataStax vector database, and the app uses LangChain.js, OpenAI and Next.js and is deployed to Vercel.
What you'll learn
- What retrieval-augmented generation is
- How vector embeddings work
- Storing and searching embeddings in a vector database
- Building a chatbot with LangChain.js and OpenAI
- Deploying a Next.js app to Vercel
