Google's New Algorithms Just Made Searching Vector Databases Faster Than Ever

A Deep Dive into how Google's ScaNN and SOAR Search algorithms supercharge the performance of Vector Databases

Image generated with DALL-E 3

Vector databases are becoming increasingly popular, especially with the increasing popularity of LLMs.

For those new to them, they are a collection of Embeddings, that are vector representations of real-world entities such as text, images, audio, videos and more.

These vector representations help capture the features and semantics of a real-world entity in a continuous vector space.

These vectors can then be used by an ML model for further processing and applications for different ML tasks.