QuestionQ13

Operational Efficiency and Optimization for GenAI Applications

A company uses Amazon Bedrock to build an AI-powered application with a foundation model (FM) that supports cross-Region inference and provisioned throughput. The application must provide consistently low latency to users in Europe and North America. It must also comply with data-residency regulations requiring European user data to stay in Europe-based AWS Regions.

During testing, the application has service degradation when Regional traffic spikes reach service quotas. The company requires a solution that preserves application resilience while minimizing operational complexity.

Which solution meets these requirements?

Explanation

Geographic Amazon Bedrock cross-Region inference profiles automatically route invocations among the supported Regions within a specified geography, such as the EU or US. This increases available throughput and handles unplanned traffic bursts without custom Regional failover logic. An EU geographic profile confines processing to EU Regions, supporting European data-residency requirements; separate regional API endpoints can direct each user population to the applicable geographic profile. Amazon Bedrock inference profiles currently do not support Provisioned Throughput.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!