Elastic brings enterprise data to NVIDIA AI factories

Elastic announced that Elasticsearch integrates with the new NVIDIA Enterprise AI Factory validated design to provide a recommended vector database for enterprises to build and deploy their own on-premises AI factories. Elastic will use NVIDIA cuVS to create a new Elasticsearch plugin that will accelerate vector search index build times and queries.

“We are obsessed with building the best vector database in the market,” said Ken Exner, chief product officer at Elastic. “NVIDIA Enterprise AI Factory validated designs enable Elastic customers to unlock faster, more relevant insights from their data.”

Elasticsearch is used throughout the industry for vector search and AI applications, with a thriving open source community. Elastic’s investment to accelerate vector search on GPUs builds upon previous longstanding efforts to optimise its vector database performance through hardware-accelerated CPU SIMD instructions, new vector data compression innovations like Better Binary Quantisation, and making Filtered HNSW faster.

“Vector databases are transforming enterprise AI by making it easier for companies to find and use information quickly,” said Pat Lee, vice president, Strategic Enterprise Partnerships at NVIDIA. “With Elasticsearch and the NVIDIA Enterprise AI Factory reference design, enterprises can unlock deeper insights and deliver more relevant, real-time information to AI agents and generative AI applications.”