Amazon S3 annotations: attach rich, queryable context directly to your objects | AWS News Blog

Open original

Amazon S3 now lets you attach multiple named annotations—structured JSON or plain text—directly to objects and manage them independently via the GetObjectAnnotation and ListObjectAnnotations APIs. This feature scales to petabytes, works across storage classes, and avoids separate metadata systems.

  • S3 now supports multiple independently-managed named annotations (JSON or text) per object via new GetObjectAnnotation and ListObjectAnnotations APIs.
  • Annotations are billed at standard S3 rates regardless of the parent object's storage class, so archiving to Glacier doesn't cut annotation costs.
  • Designed to eliminate the need for a separate metadata database by keeping context like media specs, AI summaries, or compliance data attached directly to the object.

Amazon S3 now lets you tag objects with multiple named annotations—small blobs of JSON or text that sit alongside the object itself. You can call them whatever you like (for example, “mediainfo” for technical specs or “ai_summary” for a text synopsis) and manage each one separately. That means one team can push codec details while another adds content labels, and neither team steps on the other’s toes. Behind the scenes you work with two new APIs: GetObjectAnnotation and ListObjectAnnotations. GetObjectAnnotation pulls down the blob you named; ListObjectAnnotations shows you every annotation attached to that object. The AWS CLI examples in the blog post show you exactly how to fetch “mediainfo” from bucket my-media-bucket for key videos/documentary-2026.mp4 into a local JSON file. You’ll pay standard S3 rates for storing annotations, even if the parent object lives in Glacier or another deep-archive tier. That keeps pricing simple but means your annotation costs follow your storage class. If you need more detail, AWS points you to the usual S3 pricing page. Think of annotations as a way to keep all your object metadata right with the object. Whether an AI agent hunting data, a media team tracking formats across millions of files, or a compliance squad archiving audit trails, you don’t need a separate database. You store context right where you store content.

Ask about this article