Jordi Mon Companys

5 criteria for choosing a vector database that will survive production

To avoid production failures, the author argues that teams must move beyond superficial benchmarks and evaluate vector databases using their specific data distributions to accurate…

HNSW vs. LSH: How Elasticsearch hits 0.99 recall@10 at 15,000 QPS — and what it costs

This article explains how Elasticsearch achieves high-performance vector search using HNSW indexing, reaching 15,000 QPS with a 0.99 recall@10 for float32 vectors. It highlights ho…