haiku.rag/haiku_rag_slim/haiku
Yiorgis Gozadinos 2d8b2cb9ed
Expose search.vector_nprobes
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.
2026-09-01 15:54:36 +03:00
..
rag Expose search.vector_nprobes 2026-09-01 15:54:36 +03:00