Amazon DataZone now supports meaning-based Semantic search

Amazon DataZone now supports meaning-based Semantic search in its business data catalog, enhancing how data users search and discover assets. With this new capability, users can search by concept and related terms, in addition to the existing keyword-based search. Amazon DataZone is a data management service for customers to catalog, discover, share, and govern data at scale across organizational boundaries with governance and access controls.

As data users are looking to solve their analytics use cases, they start their journey with the search in the business data catalog to understand what data is available. With this launch, users can discover related datasets in Amazon DataZone based on the intent of the user’s query. For example, a search for “profit” now returns data assets related to sales, costs, revenue in addition to the keyword profit. This significantly improves the relevance and quality of the search results and helps support the desired analytics use case. Amazon DataZone’s semantic search feature is powered by a GenAI search engine. This search engine uses an embedded language model to generate sparse vectors which enrich assets with semantically related terms.

Semantic search is available in all AWS Regions where Amazon DataZone is available.

To learn more, visit Amazon DataZone and get started using the guide in documentation.