Amazon Bedrock Data Automation is now generally available

Today, we are announcing the general availability of Amazon Bedrock Data Automation (BDA), a feature of Amazon Bedrock that enables developers to automate the generation of valuable insights from unstructured multimodal content such as documents, images, video, and audio to build GenAI-based applications. By leveraging BDA, developers can reduce development time and effort, making it easier to build intelligent document processing, media analysis, and other multimodal data-centric automation solutions. BDA can be used as a standalone feature or as a parser in Amazon Knowledge Bases RAG workflows. Further, Amazon Q Business now uses BDA to process multimodal assets and deliver insights.

In this GA release, we improved document accuracy across a variety of document types, enhanced scene-level and full video summarization accuracy, added support for detection of 35,000+ company logos in images and videos, and added support for AWS cross-region inference to optimize routing across regions within your geography to maximize throughput. BDA also added a number of security, governance, and manageability capabilities such as AWS Key Management Service (KMS) Customer Managed Keys (CMKs) support for encryption, AWS PrivateLink to connect directly to the BDA APIs in your virtual private cloud (VPC) instead of connecting over the internet, and tagging of BDA resources and jobs to track costs and enforce tag-based access policies in Amazon Identity and Access Management (IAM).

Amazon Bedrock Data Automation is now generally available in the US West (Oregon) and US East (N. Virginia) AWS Regions.

To learn more, visit the Bedrock Data Automation page.