Ben Trent
banner
benwtrent.bsky.social
Ben Trent
@benwtrent.bsky.social
Doer of things | Builder of things | software engineer
@elastic
Sounds like fun!
May 15, 2025 at 11:34 PM
Lucene will now intelligently merge HNSW graphs: elastic.co/search-labs/... Now indexing and merging is much cheaper, reducing the compute required and improving indexing throughput
April 8, 2025 at 12:57 PM
Read more about it here: elastic.co/search-labs/...

And yes, my child did the header art work. I much prefer it to yet another piece of AI generated guff. Though, the "acorn" that the "squirrel" is holding got cropped out. 🙈
Filtered HNSW & kNN search: Making searches faster - Elasticsearch Labs
Explore the improvements we have made for HNSW vector search in Apache Lucene through our ACORN-1 algorithm implementation.
elastic.co
February 28, 2025 at 3:39 PM
This this new algorithm, we have seen 3-5x fewer vector operations to achieve the same recall on previously horribly performing filter percentages.
February 28, 2025 at 3:39 PM
We have implemented a variation of the ACORN-1. arxiv.org/abs/2403.04871 The key idea is expanding your HNSW neighborhood search, and only score candidates matching your filter criteria.
February 28, 2025 at 3:39 PM
This also shows the beauty of OpenSource software. Out of nowhere Leo (github.com/aoli-al) comes to save the day, finding and helping fix tricky concurrency bugs in Apache Lucene.
aoli-al - Overview
aoli-al has 119 repositories available. Follow their code on GitHub.
github.com
February 7, 2025 at 3:59 PM
Fray is honestly pretty easy to use, provides deterministic play back of concurrency failures, and automatically detects any concurrency failures through sequential execution of threads: github.com/cmu-pasta/fray
GitHub - cmu-pasta/fray: A controlled concurrency testing framework for the JVM
A controlled concurrency testing framework for the JVM - cmu-pasta/fray
github.com
February 7, 2025 at 3:59 PM