ElasticNewCost and speed
Fewer bits, same recall: More conservative auto-calibration sweeps for DiskBBQ
Our short summary of Elastic’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on elastic.co (opens in a new tab)Problem
Vector search needed cheaper quantization without hurting recall.
Solution
Elastic adjusted its cost model to favor document bits and added preconditioning, enabling lower‑bit encodings and less reranking while keeping recall stable.
Recall@10 within 3 points, up to 11‑point gain
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on elastic.co (opens in a new tab)