Amazon Bedrock Knowledge Bases now supports cross-region inference
News
The article announces a new cross-region inference feature for Amazon Bedrock Knowledge Bases that enables developers to manage traffic bursts by utilizing compute across different AWS Regions.
Specifically, the article covers:
- Cross-region inference allows higher throughput limits and enhanced resilience during peak demand periods
- Developers no longer need to predict demand fluctuations, as traffic is dynamically routed across regions
- To use cross-region inference, specify an inference profile as the "modelARN" in the RetrieveAndGenerate API request
- No additional routing cost for using cross-region inference, charged based on the source region
- Lists supported models and pre-defined regions, provides links to documentation and blog for getting started
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.