Making Sense of Vector Databases

Vector databases are quite a hot topic these days. From powering semantic search to recommendation systems and from anomaly detection to clustering, all of this can be achieved with vector databases. But how do they do this? Join this talk to find out.

We start with understanding what a vector is and create a simple example of how vectors can be used. Then we discuss new concepts around vectors and make the examples slightly more complex each time we add a new concept to it. Finally taking the examples to an incredibly amazing level!

All in all, this talk will explain what vectors are, how are they stored, what are embedding models, indexing algorithms and similarity/distance metrics with the help of interesting examples with increasing complexity that keeps you intrigued!