Building RAG-Powered Web Apps with LlamaIndex

Retrieval-Augmented Generation (RAG) is a method of enhancing the capabilities of generative models by integrating information retrieved from external datasets or documents. LlamaIndex is a data framework for integrating Large Language Models (LLMs) with various sources, and is an easy way to utilize RAG in popular LLMs like OpenAI GPT.

In this meetup, we will learn about the concepts of RAG and other methods for teaching an LLM about our data. We will then build a RAG-powered Chat experience using LlamaIndex and Next.js, and use it to navigate an Android app’s codebase.

Speaker:
Daniel Bank