Posted On: May 21, 2024
You can now run OpenSearch version 2.13 in Amazon OpenSearch Service. With OpenSearch 2.13, we have made several improvements to search performance and resiliency, OpenSearch Dashboards and added new features to help you build AI-powered applications. We have introduced concurrent segment search that allows users to query index segments in parallel at the shard level. This offers improved latency for long-running requests that contain aggregations or large ranges. You can now index quantized vectors with FAISS-engine-based k-NN indexes, with potential to reduce memory footprint by as much as 50 percent with minimal impact to accuracy and latency. I/O-based admission control proactively monitors and prevents I/O usage breaches to further improve the resilience of the cluster.
This launch also introduces several features that enable you to build and deploy AI-powered search applications. The new flow framework, helps you to automate the configuration of search and ingest pipeline resources required by advanced search features like semantic, multimodal, and conversational search. This adds to existing capabilities for automating ml-commons resource setup, allowing you to package OpenSearch AI solutions into portable templates.
For information on upgrading to OpenSearch 2.13, please see our documentation. OpenSearch 2.13 is now available in Amazon Web Services China (Beijing) Region, operated by Sinnet and Amazon Web Services China (Ningxia) Region, operated by NWCD.
To learn more about Amazon OpenSearch Service, please visit the product page.