UltraBERT Fits 32K Tokens in One Vector. RIP Chunking?
Dylan Couzon, Anush
October 19, 2026
Qdrant 1.20 - Full-Text Search Improvements
Andrey Vasnetsov
October 22, 2026
- Products
- Solutions
- Resources
- Company
Qdrant Blog
SHIFTing Languages in Multilingual RAG
Fix multilingual embedding language bias with SHIFT: shift document and query vectors to one pivot language and store them in a single Qdrant index.
Evgeniya Sukhodolskaya
September 16, 2026
Enough with the Bad Benchmarks: Tools for Production-Grade Research
Qdrant and Vultr release Qdrant-FineWeb-10B, the largest open-source vector search benchmark, plus Supernova, an open-source framework for embedding generation, ground truth, and evaluation at billion-vector scale.
Qdrant Labs
September 01, 2026
How to Tune Vector Search Without Guessing
Tune retrieval in Qdrant: the measurement behind fusion k, candidate depth, rerankers, rescoring, and labeled set size.
Dylan Couzon
August 24, 2026
How Bayer Built an Enterprise-Scale Search Engine with Qdrant
How Bayer built myGenAssist on Qdrant Hybrid Cloud: 135M points, hybrid search for deep agents, semantic caching, multitenancy, and a 20% efficiency gain.
Daniel Azoulai
August 13, 2026
Qdrant and Minima Deliver 2.92x More Agentic RAG Tasks per GPU-Hour
Hybrid search, payload filters, and late-interaction reranking in Qdrant plus Minima-optimized inference delivered 2.92x more successful agentic RAG tasks per GPU-hour without reducing grounded quality.
Qdrant and Minima Engineering
August 13, 2026
How to Clean Up a Qdrant Collection
Clean up a vector database collection: control duplicate points, track embedding provenance, remove stale records, and protect top-k search quality.
Dylan Couzon
August 10, 2026
Pre-Filtering vs Post-Filtering (and Why Qdrant Does Neither)
Compare pre-filtering vs post-filtering in vector search: where each breaks, how Qdrant filters in place, and when ACORN earns its cost.
Dylan Couzon
August 07, 2026
Qdrant 1.19 - TurboQuant Datatype & Memory Tiers
Version 1.19 of Qdrant introduces the TurboQuant datatype for major storage savings, unified memory tier configuration, replica read affinity, and full-text search enhancements.
Andrey Vasnetsov
August 05, 2026
Lessons From Building E-Commerce Search on Qdrant
Build e-commerce search on Qdrant: lessons on hybrid ranking, in-query filtering, embedding recipes, personalization as re-rank, and merchandising formulas.
Dylan Couzon
July 24, 2026
Get Started with Qdrant Free
Get Started