// AI news · 2026-11-02 · Dev.to LLM
Qdrant 1.20 Adds BM25 Keyword Ranking in Full-Text Index
Qdrant 1.20 integrates BM25 keyword ranking directly into its full-text index, computing statistics on-the-fly to maintain accurate scoring during data updates.
Published 2026-11-02 03:00 (Beijing time)Source Dev.to LLMAuto-summarised, fact-checked against source
01Summary
It introduces a code tokenizer that splits identifiers at underscores and case boundaries, enabling better source code retrieval. Text queries support dynamic k and b parameter tuning per query, while per-element indexes improve nested filter performance by 7–38x. TurboQuant types reduce vector storage size without sacrificing recall@10.
Summarised from the original article by an open-source model, then checked automatically: every number and English name must appear in the source. The original article is authoritative.
02Key points
- BM25 ranking now runs directly in full-text index with on-the-fly statistics.
- Code tokenizer splits identifiers at underscores and case boundaries for better source code matching.
- Query-level k and b parameters allow dynamic tuning without index rebuild.
- Per-element indexes enable 7–38x faster nested filter performance.
03Source
Qdrant 1.20 Ranks Keyword Matches Inside the Full-Text Index
Dev.to LLM · published 2026-11-02 03:00 Beijing time
05Related news
- Same source · LLMs, Jev, CDMs: Three Answering Models Compared2026-11-02 · Dev.to LLM
- Same source · Types and Methods of AI Evaluations2026-11-02 · Dev.to LLM
- Same topic · Understanding Coefficient of Variation2026-11-02 · Dev.to AI
- Same topic · Adding Chromecast MAC & State to UI Components2026-11-02 · Dev.to AI
- Same day · AI Reflects on Unsourceable Thoughts in Its Record2026-11-02 · Dev.to AI
From AIMap AI news: collected from 1,100+ official and media sources. Summaries only restate the original article; follow the link for the full story. All stories of 2026-11-02 · Archive by date · All AI news · Today