Making RAG Work - Building Robust Retrieval Augmented Generation Systems
Toronto Machine Learning Series (TMLS) via YouTube
Overview
Learn how to effectively implement RAG (Retrieval Augmented Generation) systems beyond prototype stages in this 30-minute conference talk from Toronto Machine Learning Series. Explore common implementation challenges and their solutions as Hudson Labs CTO Suhas Pai demonstrates techniques for building robust RAG pipelines. Discover methods to balance system performance with practical considerations like latency and cost while understanding key pitfalls to avoid when developing LLM-based applications using the RAG paradigm.
Syllabus
Making RAG Retrieval Augmented Generation Work
Taught by
Toronto Machine Learning Series (TMLS)