Note: this video presentation is based on my survey of Vector Databases.
Last week at the NLP Meetup organized by deepset I’ve presented on the Landscape of Vector Databases and neural search frameworks. Max Irwin was my co-presentor to deep-dive into the BuddyPQ algorithm we have invented together as part of Sisu Team during Billion-Scale Approximate Nearest Neighbour Search Challenge. The main achievement of our algorithm is 12% higher recall over baseline FAISS algorithm.
You can watch the recording here:
And here are the slides: