Developing RAG Apps with LlamaIndex and JS

Overview

In this course, you will learn how to build Retrieval-Augmented Generation (RAG) applications using LlamaIndex and JavaScript. Starting with an introduction to the course structure and prerequisites, you’ll dive straight into hands-on learning to build production-ready apps.

By the end of the course, you will be able to integrate various data sources, set up an OpenAI account, and use powerful tools such as the RouterQueryEngine to handle advanced queries. The course starts with setting up your development environment with NodeJS and OpenAI.

You'll be introduced to LlamaIndex, explore its core features, and quickly dive into the fundamentals of RAG systems, from data ingestion and indexing to querying and building custom RAG systems. Along the way, you’ll gain in-depth knowledge of how to handle different types of data, such as PDFs, and how to interact with your system using an Express API.

As you progress, you'll tackle more advanced concepts like handling multiple query engines, using agents, and incorporating production-level techniques to make your RAG apps robust and scalable. The course culminates in building a full-stack chatbot app with NextJS and deploying it to Vercel.

You’ll leave the course with the ability to develop, deploy, and maintain sophisticated RAG applications. This course is ideal for developers with a solid understanding of JavaScript and basic web development concepts who wish to learn more about RAG systems and their application in real-world projects.

No prior experience with LlamaIndex is necessary, but familiarity with NodeJS and APIs is recommended.

Syllabus

• Introduction
In this module, we will introduce the course, discuss the prerequisites, outline the structure, and preview the exciting projects you’ll be building. You’ll gain an overview of the course and an understanding of the learning path ahead.
• Development Environment Setup
In this module, we will guide you through the setup of your development environment, focusing on NodeJS installation and OpenAI API key configuration. This foundation will prepare you for the hands-on work ahead.
• LlamaIndex Deep Dive – Fundamentals
In this module, we will take a deep dive into LlamaIndex, focusing on its key features and functionality. You'll learn the core workflow and set up your first simple RAG system using LlamaIndex.
• LlamaIndex Deep Dive - Main Concepts and Data Loaders
In this module, we will cover the main concepts behind LlamaIndex and demonstrate how to build custom RAG systems, work with structured data, and query PDFs. You’ll also create an Express API to interact with your system.
• Agents & Advanced Queries with LlamaIndex
In this module, we will explore advanced querying techniques, including the RouterQueryEngine and how to handle multiple data sources. You’ll build more complex systems and query tools for sophisticated interactions with your RAG systems.
• Persist Your Data & Production-ready Techniques
In this module, we will focus on ensuring your RAG system is production-ready. You’ll learn how to manage persistent data and apply advanced techniques to optimize system performance.
• NextJS Full-stack Web Application Chatbot with One Command & Deployment
In this module, we will walk through building a full-stack chatbot app using NextJS, customizing it with your own data, and deploying it to Vercel for production use. You’ll learn to streamline the process with the create-llama CLI command.
• Wrap up
In this final module, we will review everything you've learned, reinforce your progress, and provide guidance on how to continue your development in the field. You'll leave with a solid foundation and next steps for further growth.

Taught by

Packt - Course Instructors

Subjects

Computer Science