Practical Tips for Building Production-Grade RAG Applications with LlamaIndex

Jerry Liu is CEO and Co-Founder of LlamaIndex, a company at the center of the revolution in AI agents.

This talk covers how LlamaIndex can serve as a Data Management and Query Engine for LLM applications. Learn about all things fine-tuning -- including finetuning embeddings, sentence_transformers, linear adapter, and LLMs -- as well as challenges with naive RAG, techniques for better-performing RAG (i.e. augmenting chunks with context and decoupling embeddings from raw text chunks), and much more.

This talk was originally delivered at “From Toy To Production: Building LLM-Powered Systems that Work in the Real World,” an event in New York City dedicated to scaling LLM-powered systems from experimental stages to real-world production environments.