I came across this AWS blog on OpenSearch K-NN — very helpful!
I’m exploring K-NN queries with filters (e.g., status = 'active'
) and wondering about performance implications.
In pgvector, there’s an “iterative index scan” explained in detail in this blog that optimizes K-NN with filters.
Does OpenSearch offer a similar optimization or guidance for such queries?
Any benchmarks or best practices would be great.