Amazon SageMaker Catalog, part of the next generation of Amazon SageMaker, now supports AI recommendations for descriptions—including table summaries, use cases, and column-level descriptions—for custom structured assets registered programmatically. This applies to a wide range of assets, for example, Iceberg tables in Amazon S3, or datasets from third-party and internal applications.
Building on existing automated metadata capabilities for harvested assets from native services like AWS Glue and Amazon Redshift, this enhancement enables users to generate business-friendly descriptions for custom assets using large language models (LLMs) via Amazon Bedrock.
With just a few clicks, users can trigger AI-generated suggestions, review and refine descriptions, and publish enriched asset metadata directly to the catalog. This helps reduce manual documentation effort, improves metadata consistency, and accelerates asset discoverability across organizations.
Learn more about how to generate automated metadata for custom assets in our product documentation.
Categories: marketing:marchitecture/artificial-intelligence,general:products/amazon-sagemaker,general:products/amazon-machine-learning
Source: Amazon Web Services
Latest Posts
- (Updated) Message Trace support on Graph API is now in Public Preview [MC1221939]
- (Updated) Microsoft 365 Copilot: Content Sources in Copilot Chat [MC1127230]
- (Updated) Microsoft Purview eDiscovery Configuration change for PowerShell cmdlet case [MC1238428]
- Amazon S3 now provides AWS source region information in server access logs
![Microsoft Copilot Studio – Publish agents to WhatsApp [MC1107311]](https://mwpro.co.uk/wp-content/uploads/2024/08/pexels-lulizler-3165335-150x150.webp "Microsoft Copilot Studio – Publish agents to WhatsApp [MC1107311] 6")
