Qdrant 1.19 Fixes Multi-Tenant BM25 Scoring Interference
qdrant_engine · x · 2026-08-10
Qdrant version 1.19 resolves an issue with BM25 scoring in multi-tenant collections. Previously, IDF (Inverse Document Frequency) was calculated globally across all tenants. If tenants used vastly different vocabularies, their statistics were mixed, degrading search accuracy.
The new version allows calculating IDF statistics per tenant. Each tenant's BM25 score is now based solely on their own data, ensuring more accurate lexical search without the need for separate collections.
More from Infra
- Inside Xanadu's Lab: Ultra-low Loss Thin Film Lithium Niobate Switch Wafers — ceciletamura · 2026-08-11
- Beyond GPUs: Rethinking the Energy and Architecture Stack for Next-Gen AI Inference — prateekj · 2026-08-11
- Running Local LLMs on Strix Halo: Are 64GB/128GB RAM Variants Practical? — riklaunim · 2026-08-11
- Open Models Matching Cloud? It's Now an Engineering Tradeoff — cocktailpeanut · 2026-08-11
- GitHub Actions Outage Last Week: Users Await Incident Report — SkyLi0n · 2026-08-11
- Wall Street Giants Partner with Nvidia on $500B AI Infrastructure Financing — firstadopter · 2026-08-11