Elastic Introduces Better Binary Quantization Technique in Elasticsearch

Elastic

Elastic, the Search AI Company, announced Better Binary Quantization (BBQ) in Elasticsearch. BBQ is a new quantization approach developed from insights drawn from a technique proposed by researchers at Nanyang Technological University Singapore called RaBitQ. Elastic’s BBQ is a distinct evolution of the ideas presented in the RaBitQ paper. It delivers advancements in quantization for Lucene and Elasticsearch, offering high-ranking quality while achieving a 95% memory reduction and similar storage offered by scalar quantization.

“Elasticsearch is evolving to become one of the best vector databases in the world, and we see our users wanting to put more and more vectorized data in it,” said Ajay Nair, general manager, Platform at Elastic. Better Binary Quantization is our latest innovation to reduce the resources needed to store vectorized data and provide freedom to our users to vectorize all the things.”

Also Read: CrowdStrike Launches AI Red Team Services to Secure AI Systems Against Emerging Threats

BBQ is now available as a tech preview in Elasticsearch for self-managed and cloud users and will be contributed to Apache Lucene.

SOURCE: BusinessWire