This chapter covers
- Building RAG apps with Next.js, Clerk, and LangChain.js
- Securing documents and isolating user data
- Using Upstash Redis and Vector for search and state
- Designing chat interfaces with text-to-speech
- Optimizing databases and prompt engineering
- Solving state sync and document-parsing issues
This project is a more complex full-stack generative AI web application: a retrieval-augmented generation (RAG) app designed to manage multiple knowledge bases. The app uses the Vercel AI SDK and LangChain.js libraries to enable users to upload documents, organize them into knowledge bases, and interact with these knowledge bases via conversational AI. The application also integrates modern authentication, persistence, and vector search technologies to ensure a more robust experience.
We start with the features and how the application behaves and then go over the technical decisions. I conclude this chapter with some important next steps to your learning path for building robust, full-stack, AI-powered web applications.
11.1 Overview of the application
Our RAG web app allows users to create, manage, and query knowledge bases composed of multiple documents (PDFs and DOCX supported). Each user can securely authenticate, create or delete knowledge bases, upload new documents to them, and chat with an AI assistant that answers questions based on the knowledge within the selected knowledge base.