UltraBERT Fits 32K Tokens in One Vector. RIP Chunking?
Dylan Couzon, Anush
October 19, 2026

Andrey Vasnetsov
October 22, 2026
Dylan Couzon, Anush
October 19, 2026
Sasha Denisov & Chadha Sridi
October 14, 2026
Dylan Couzon, Anush
October 13, 2026

A guide on how you can run a small static embedding model on an ESP32 chip with 16MB of flash memory using `no_std` Rust
Clelia Bertelli
November 11, 2026

Measurements of Qdrant 1.20 performance: turbo8 and turbo16 match float32 recall at a quarter and half of the storage, and per-element indexes make nested filters up to 4 times faster.
Clelia Bertelli
November 02, 2026

Use Cohere embeddings for visual PDF retrieval in Qdrant. Compare ViDoRe results and combine small vectors in RAM with full vectors on disk.
Evgeniya Sukhodolskaya
October 23, 2026

How Poliscope indexed about 4,800 German council portals into one self-hosted Qdrant collection of 130M points: hybrid search, tenant and prefix filtering, and TurboQuant on one bare-metal server, taking mean search time from 20 seconds to 0.87 seconds.
Daniel Azoulai
October 15, 2026

We applied the Jev generalized classifier to reranking, query understanding, near-duplicate removal, and semantic chunking.
Andrei Cristea & Chadha Sridi
October 08, 2026

Google's EmbeddingGemma 2 in Qdrant: 99% of retrieval quality in 30x less vector RAM, or 94.5% in 77x less with rescoring.
Qdrant Team
October 06, 2026

Swap query models without re-embedding documents. Explore Constella Zero, Nano, and Stella, with BEIR-15 results and CPU benchmarks.
Dylan Couzon
September 29, 2026

Learnings from writing a cross-encoder inference library in Rust and comparing it with existing Python packages.
Clelia Bertelli
September 25, 2026

How Lucy built a retrieval layer over 2.8M+ SEC and DART filings on Qdrant: four-lane hybrid search, payload filtering, and TurboQuant, reaching 94.7% Recall@10 on FinanceBench.
Daniel Azoulai
September 21, 2026