How AI Is Built cover image

#030 Vector Search at Scale, Why One Size Doesn't Fit All

How AI Is Built

00:00

Scaling Vector Databases

This chapter examines the complexities of scaling vector databases, focusing on the transition from single-instance to distributed systems to handle massive data volumes. It discusses challenges of maintaining consistency and performance, particularly with the Raft consensus algorithm, and highlights the importance of balancing various indexing strategies and GPU acceleration for optimizing vector searches. The discussion also addresses the evolution of embeddings and the need for advanced similarity measures in modern vector search systems.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app