February 25-27, 2026
Montreal, Canada
RAG That Works: Fixing Vector Search with L2 Normalization
Most Retrieval Augmented Generation (RAG) systems ship broken: embeddings without L2 normalization produce wildly inaccurate results. This talk shows why normalization matters, how to implement it in production (pgvector, TypeScript, Cloudflare Workers), and the massive accuracy gains it unlocks. Attendees will leave with practical patterns to avoid silent failure in their AI pipelines.
Nicholas Nadeau
Onix
Dr. Nicholas Nadeau is an engineer and builder developing systems that enhance human intelligence across humanoid robots, cognitive neuroscience devices, and privacy-first AI. He scaled 3D printers at AON3D with parts on the ISS and Moon, led humanoid robots as CTO of 1X, and later served as CTO at SmartOne.ai. Now Co-Founder & CTO of Onix building Personal Intelligence, he also co-founded AI Salon Montréal, mentors at CDL, Next AI, Startupfest, and serves on the board of Garage&Co.
