Posted On: Oct 27, 2023

Users can now benefit from more efficient query filtering with OpenSearch’s k-NN FAISS engine by using OpenSearch 2.9 on the Amazon OpenSearch Service. Previously exclusive to OpenSearch’s Lucene k-NN engine, OpenSearch’s efficient vector query filters capability intelligently evaluates optimal filtering strategies—like pre-filtering with approximate nearest neighbor (ANN) or filtering with exact k-nearest neighbor (k-NN)—to determine the best strategy to deliver accurate and low latency vector search queries. In earlier OpenSearch versions, vector queries on the FAISS engine used post-filtering techniques, which enabled filtered queries at scale, but it potentially returns less than the requested “k” number of results.

Efficient vector query filters have demonstrated the ability to deliver low latency and accurate results enabling customers to create more responsive vector search applications such as semantic or visual search experiences. Vector query filters is a key enabler for hybrid search empowering users to perform vector search while filtering on metadata to retrieve more relevant information using both vector and lexical techniques. This new feature enhances OpenSearch’s existing query filtering capability by providing improved accuracy and speed. 

Efficient vector query filters for FAISS is available in all AWS Regions where Amazon OpenSearch Service is available. For more information about vector query filtering support on OpenSearch, refer to the documentation.