v.25.10Experimental Feature
QBit data type
ImplementQBitdata type that stores vectors in bit-sliced format andL2DistanceTransposedfunction that allows approximate vector search where precision-speed trade-off is controlled by a parameter. #87922 (Raufs Dunamalijevs).
Why it matters
This feature addresses the need for efficient vector storage and fast approximate similarity search in ClickHouse. By using a bit-sliced representation for vectors viaQBit, and providing the L2DistanceTransposed function that allows users to control the balance between search accuracy and performance, it enhances ClickHouse's capability to perform large-scale vector similarity queries more efficiently.How to use it
Users can define table columns using theQBit data type to store vectors in bit-sliced format. For approximate nearest neighbor search, they can use the L2DistanceTransposed function in their queries, adjusting its parameter to control the trade-off between result precision and query speed.