What if we store vector embeddings vertically?
By using a columnar layout for vectors, you can speed up vector similarity search thanks to the more efficient distance kernels and efficient pruning of dimensions. This entry is a summary of our work, PDX: A Data Layout for Vector Similarity Search. A few months ago, we came across this 20-year-old paper proposing a vertical layout for vectors. That means not storing vectors one after the other but storing the same dimension of different vectors together (see image above). In databases, this is referred to as “columnar storage.” ...