The IVF probe count was the one vector search parameter with no setting, and it is what bounds recall on a large indexed corpus: partitions grow with the corpus, so a fixed probe count covers less of it, and vector_refine_factor can only re-score what the probes returned. Defaults to 20, matching lance, so search is unchanged. Also corrects the create-index docs, which predate the measurement: optimize() covers new chunks, so a rebuild is about retraining centroids rather than reaching unindexed rows. |
||
|---|---|---|
| .. | ||
| capabilities | ||
| configuration | ||
| img | ||
| stylesheets | ||
| apps.md | ||
| benchmarks.md | ||
| changelog.md | ||
| chat.md | ||
| cli.md | ||
| custom-pipelines.md | ||
| development.md | ||
| index.md | ||
| ingester.md | ||
| installation.md | ||
| mcp.md | ||
| overview.md | ||
| python.md | ||
| remote-processing.md | ||
| tools.md | ||
| tuning.md | ||
| tutorial.md | ||