Blog
Vector quantization auto-calibration
Elasticsearch picks vector quantization parameters for each segment instead of asking you to tune them. These posts cover the recall model, the merge-time sweep, and the cost model behind it.
How Elasticsearch auto-tunes vector quantization to hit your recall target
Elasticsearch Labs
How Elasticsearch auto-tunes vector quantization to hit your recall target
Learn the geometric model that lets Elasticsearch predict recall with R² > 0.98 accuracy and auto-select vector quantization parameters from a small data sample.
17% faster search, zero config: auto-calibrating vector quantization in Elasticsearch
Elasticsearch Labs
17% faster search, zero config: auto-calibrating vector quantization in Elasticsearch
Automatic calibration at merge time picks vector quantization parameters for each segment by predicting recall from a small sample. Here's how we built it into Elasticsearch's merge path.