Learn how to build a RAG application in JavaScript, and use an intelligent agent that discerns and selects from multiple data sources to answer your queries.
We'd like to know you better so we can create more relevant courses. What do you do for work?
Instructor: Laurie Voss
Learn how to build a RAG application in JavaScript, and use an intelligent agent that discerns and selects from multiple data sources to answer your queries.
Build a full-stack web app with an interactive frontend component that interacts and chats with your data.
Learn how to persist your data, enable chatting with your data and make streaming responses possible, all implemented using the create-llama command-line tool.
Get started building full-stack RAG web applications. This course introduces the basics of Retrieval Augment Generation (RAG), including its practical implementation with JavaScript. You’ll assemble an intelligent agent capable of running its own queries. This course will guide you through the process of building a full-stack JavaScript web application, from the API server to a React component that queries your data. You’ll also learn to develop persistent chat that streams your answers to an interactive front-end in real time.
Learn from Laurie Voss, VP of developer relations at LlamaIndex, web developer and the co-founder of npm, the central registry of JavaScript packages.
In this course:
Start building RAG web applications in JavaScript that allow you to interact with your data using LlamaIndex.
Anyone who has basic JavaScript knowledge who wants to explore RAG application development and to quickly build a full-stack web application using LlamaIndex!
Introduction
Getting started with RAG
Build a full-stack web app
Advanced queries with Agents
Production-ready techniques
Conclusion
Course access is free for a limited time during the DeepLearning.AI learning platform beta!
Keep learning with updates on curated AI news, courses, and events, as well as Andrew’s thoughts from DeepLearning.AI!