Elastic adopts more efficient approach for storing vectorized data

Elastic is implementing a new approach for storing vectorized data that will require 95% less memory.  Better Binary Quantization, or BBQ, is based on a technique called RaBitQ, which was developed earlier this year by researchers at Nanyang Technological University Singapore.  According to Elastic, the biggest differences between BBQ and native binary quantization are that: … appeared first on SD Times.