12-06, 15:00–16:00 (UTC), Data Track
Large Language Models (LLMs) are revolutionizing how users can search for, interact with, and generate new content. Some recent stacks and toolkits around Retrieval-Augmented Generation (RAG) and agents, enabling users to build applications such as chatbots using LLMs on their private data. In this talk we do a comprehensive survey of both basic and advanced RAG techniques. We show you what RAG is and how to setup a simple version. We show you how to evaluate and optimize RAG systems. We then talk on advanced concepts (agents, fine-tuning), and help you think about how to build a full-stack LLM app.
This is the keynote by Jerry Liu
No previous knowledge expected
Jerry is the co-founder/CEO of LlamaIndex, a data framework for building LLM applications. Before this, he has spent his career at the intersection of ML, research, and startups. He led the ML monitoring team at Robust Intelligence, did self-driving AI research at Uber ATG, worked on recommendation systems at Quora, and graduated from Princeton.