Players in Vector Search: Video

In July I got an invitation from the Sease team to present at the London IR Meetup, where I spoke about players, algorithms, software and use cases in Vector Search.

In this presentation I’ve used the opportunity to give an update on the first season of Vector Podcast: it has been fascinating to talk to the makers in the field of Vector Search as well as to follow their progress and see new players emerge.

Beside diving into the algorithms powering various players, like Vector Databases and Neural frameworks, I have also given two demos:

1. Multilingual book search built on top of FAISS using Amazon books data.
2. Multilingual and multimodal search built on top of scalable GSI APU and OpenSearch using LAION web-crawled imagery data.

Recording:

Slides:

Hope you’ll enjoy this piece, and curious to learn what use cases you see in your practice, as well as architecture setup in your practice / experimentation.