Elastic announced the launch of the Elasticsearch Relevance Engine (ESRE), with built-in vector search and transformer models, which is designed to bring AI innovation to proprietary enterprise data. ESRE enables companies create secure deployments to take advantage of all their proprietary structured and unstructured data.
Elastic has made investments in foundational AI capabilities to democratize AI and machine learning for developers with a Unified APIs for vector search, BM25f search and hybrid search, plus a transformer model small enough to fit on a laptop’s memory.
Using a relevance engine, like ESRE, allows companies to take advantage of all of their structured and unstructured data to build custom generative AI (GAI) apps, without having to worry about the size and cost of running large language models. The ability to “bring your own” transformer model and integrate with third-party transformer models allows organizations to create secure deployments that leverage GAI on their specific business data. With ESRE, the companies and community of users that have invested in Elastic solutions can advance AI initiatives right now without a lot of additional resources.