The latest version of OpenSearch, 2.13, is now available on Amazon OpenSearch Service. This update brings improvements to search performance and resiliency, as well as new features to support the development of AI-powered applications. One key enhancement is concurrent segment search, which enables users to query index segments in parallel at the shard level, resulting in improved latency for large aggregations or ranges. Additionally, the ability to index quantification vectors with k-NN indices using the FAISS engine can reduce memory usage by up to 50 percent with minimal impact on accuracy and latency.
Another notable feature is I/O-based admission control, which proactively monitors and prevents I/O usage violations to enhance cluster resiliency. OpenSearch 2.13 also includes tools for creating and deploying AI-powered search applications. The new flow framework automates search setup and ingestion processes for advanced search capabilities like semantic, multimodal, and conversational search. Furthermore, predefined templates are available to automate model configuration and integration with APIs such as OpenAI, Amazon Bedrock, and Cohere, enabling the development of solutions like semantic search.
For those interested in upgrading to OpenSearch 2.13, detailed documentation is available. The latest version is accessible in all AWS Regions where Amazon OpenSearch Service is offered. With these enhancements and new features, users can leverage OpenSearch to optimize search performance, enhance resiliency, and build innovative AI-powered applications.
Article Source
https://aws.amazon.com/about-aws/whats-new/2024/05/amazon-opensearch-supports-opensearch-version-2-13/