LectureRechercheRadarCadre d'investissement
Connexion / Inscription
← Retour à la lecture
ActualitésPrise rapide1 min de lectureRédaction DisconfirmAI

Neo4j makes binary quantization the default, cutting vector search memory

Neo4j 2026.09 makes rescored binary quantization the default for new vector indexes; vendor-run tests claim ~4x vectors per memory budget, methodology still unpublished.

2026-09-23 19:06 GMT+8

Starting with Neo4j 2026.09, rescored binary quantization is the default for newly created vector indexes in Aura, Enterprise Edition and Community Edition.

In vendor-run benchmarks, Neo4j claims roughly five times better throughput and query latency than 2026.08, and about four times as many 768-dimensional Float32 embeddings fitting in the same memory budget. The approach searches compressed binary vectors first, then rescores candidates against full-precision vectors read from disk.

All figures are Neo4j's own first-party benchmarks; the methodology post has not been published and nothing is independently verified. The technique draws on RaBitQ from NTU and the BBQ implementation in Lucene.

Sources

  • neo4j.com↗
Continuer la recherche →
Connexion / Inscription
LectureRechercheRadarCadre d'investissement