Developing RAG Apps with LlamaIndex and Next.js
2h 40mIntermediate2026-02-27
Authors
Packt Publishing
Course details
What is this course about?
Explore the development of retrieval-augmented generation (RAG) applications using LlamaIndex and JavaScript. After reviewing the prerequisites and project goals, focus on setting up the development environment, including configuring Node.js and obtaining OpenAI API keys to facilitate seamless interaction with LlamaIndex. Then dive into LlamaIndex fundamentals, like data ingestion, indexing, and querying. Follow along to build basic and custom RAG systems, query structured data, and interact with LlamaIndex using an Express API. The exercises equip you to handle complex scenarios, such as querying PDF files and integrating multiple data sources. The final sections focus on advanced topics, including managing data persistence and deploying production-ready applications. You’ll learn how to create a full-stack chatbot app with Next.js, utilizing the create-llama CLI for rapid setup and customization. By the end, you'll be able to build, customize, and deploy scalable RAG applications.
Objectives
What will I be able to do by the end of this course?
Create RAG systems with LlamaIndex and JavaScript.
Set up and configure a full development environment for RAG apps.
Implement data ingestion and indexing techniques using LlamaIndex.
Build complex LlamaIndex queries with custom data loaders and engines.
Develop a full-stack chatbot with Next.js, LlamaIndex, and OpenAI.
Deploy scalable RAG systems with persistent data for production use.
Audience
Who is this course for?
Software developers
AI engineers
Machine learning engineers
Data scientists
Web developers
Technology enthusiasts interested in AI integration
IT professionals focused on scalable solutions
Prerequisites
What do I need to know before taking this course?
Basic knowledge of JavaScript and web development
Familiarity with APIs and backend development concepts
Foundational understanding of AI or machine learning concepts is helpful but not required
Explore the development of retrieval-augmented generation (RAG) applications using LlamaIndex and JavaScript. After reviewing the prerequisites and project goals, focus on setting up the development environment, including configuring Node.js and obtaining OpenAI API keys to facilitate seamless interaction with LlamaIndex. Then dive into LlamaIndex fundamentals, like data ingestion, indexing, and querying. Follow along to build basic and custom RAG systems, query structured data, and interact with LlamaIndex using an Express API. The exercises equip you to handle complex scenarios, such as querying PDF files and integrating multiple data sources. The final sections focus on advanced topics, including managing data persistence and deploying production-ready applications. You’ll learn how to create a full-stack chatbot app with Next.js, utilizing the create-llama CLI for rapid setup and customization. By the end, you'll be able to build, customize, and deploy scalable RAG applications.
Objectives
What will I be able to do by the end of this course?
Create RAG systems with LlamaIndex and JavaScript.
Set up and configure a full development environment for RAG apps.
Implement data ingestion and indexing techniques using LlamaIndex.
Build complex LlamaIndex queries with custom data loaders and engines.
Develop a full-stack chatbot with Next.js, LlamaIndex, and OpenAI.
Deploy scalable RAG systems with persistent data for production use.
Audience
Who is this course for?
Software developers
AI engineers
Machine learning engineers
Data scientists
Web developers
Technology enthusiasts interested in AI integration
IT professionals focused on scalable solutions
Prerequisites
What do I need to know before taking this course?
Basic knowledge of JavaScript and web development
Familiarity with APIs and backend development concepts
Foundational understanding of AI or machine learning concepts is helpful but not required
Concepts
Introduction
- Introduction
- Course prerequisites and who is this course for
- Course structure
- Please watch - What you'll build in this course
Development Environment Setup
- Set up dev environment - Node.js instructions
- Setup OpenAI account and the OpenAI API key
LlamaIndex Deep Dive - Fundamentals
- Deep dive into LlamaIndex and key features - Overview
- RAG crash course
- LlamaIndex flow - Overview
- LlamaIndex - Data ingestion, indexing and query interface overview
- Hands-on - Set up LlamaIndex simple RAG system
- Summary
LlamaIndex Deep Dive - Main Concepts and Data Loaders
- LlamaIndex core concepts - Loaders index
- The querying stage - Overview
- Querying stage - ChatEngine and querying engine full overview
- Hands-on - Create a custom RAG system with LlamaIndex
- Hands-on - Structured data extraction
- Hands-on - Querying a PDF file
- Hands-on - Interacting with a RAG system through an Express API, full hands-on
- Summary
Agents and Advanced Queries with LlamaIndex
- Agents and advanced queries - The RouterQueryEngine overview
- Hands-on - RAG system with multiple data sources
- Hands-on - Creating a RouterQueryEngine to handle multiple query engines
- Hands-on - Defining functions and querying tools to start chatting with the agent
Persist Your Data and Production-Ready Techniques
- Production-ready techniques - Introduction
- Hands-on - Data with LlamaIndex
- Hands-on - Load index with the persisted data and stream response
- Summary
NextJS Full-stack Web Application Chatbot with One Command and Deployment
- Chatbot app with Next.js - Full-stack web app, overview
- Hands-on - Generating a full-stack web app with create-llama CLI command
- Hands-on - Customizing the app with your own data and chatting with it
- Hands-on - Deploying our Next.js full-stack chat app to Vercel
Wrap up
- Wrap up and next steps