Andrew introduces a new LlamaIndex course on building JavaScript RAG web apps. Instructor Lori Voss, VP of Developer Relations at LlamaIndex and npm co-founder, teaches the full RAG pipeline from vector indexing through LLM calls, plus agent techniques and building a React frontend with persistent chat.
I'm delighted to introduce JavaScript rag web apps with Llama Index. Both in partnership with Llama Index and taught by Orey Voss. This course walks you through, step by step, how to build a Full Stack web application that lets you chat with your data because we'll be building a web application, we'll be using JavaScript. But if you're familiar with coding, even if you haven't used JavaScript before, you'll still be able to follow along. A RAG application loosely has five steps. First, doing pre processing, you load your data from wherever it lives and then index that data into vectors and store it. Then, after you get a query, you retrieve the most relevant context using vector search and then send that context and your query to an LLM to generate an answer. And then finally and optionally, you can further process the response you get by maybe turn it into JSON. For instance, we'll be showing the components of llamaindex that let you achieve all of these steps. In addition, you also learn more advanced agent techniques to not just query from the same database every time, but to dynamically select from multiple data sources like multiple databases, or even the possibility of making specialized function calls to retrieve information for a query within Switchtracks t web development and show you the basics of building a backend web API and an interactive REACT component that can query that API on the front end and how to put it all together into a Full Stack web application. I'm delighted to introduce the instructor, Lori Voss, who is Vice President of Developer Relations at Llama Index. Lori has been a Web developer for 27 years and was one of the co founders of NPM, the Central Registry of JavaScript Packages. So his work has had a massive impact on how people build web apps.
Thanks Andrew. So in this course you'll start with the basics of retrieval, augmented generation, what it is, why you do it, and how it works. You'll immediately jump in and run some RAG queries on your own data and take it to the next level by building an intelligent agent that can run its own queries in parallel. You will learn how to build a Full Stack web application, starting with a basic API server and a REACT component that queries that API and moving to persistent chat streams your answers to the front end in real time.
One of the most in demand applications available right now is building RAG applications. With this course you learn not just best practices for Rag, but also how to build a JavaScript web app to serve up results. To use this, please check it out.
Let's get started.
