FROM THE TEAM
Marek Galovic
Writing on search, retrieval, and building TopK.
The Fastest Regex Is the One You Don’t Run
Why AI agents reach for regex search, and how TopK uses sparse n-grams to make those queries fast.
RAG Is Broken for Agents. Here's How We Fixed It.
Context is a search problem. Without the right context, even the best models fail. This post describes why dense embedding based RAG is broken for agents and how multi-vector (late interaction) retrieval fixes it.
SMVE: Multi-Vector Retrieval That Just Works
TopK introduces SMVE, a fast and scalable approach to late-interaction retrieval based on sparse random projections.
[Podcast] Building a Search Database from First Principles
Listen to our founder Marek Galovic discuss the challenges and solutions in building a search database from the ground up, covering everything from vector search to hybrid retrieval and the architectural decisions that shaped TopK.
Beyond RRF: How TopK Improves Hybrid Search by up to 7.8%
A case study on how TopK hybrid retrieval outperforms traditional RRF-based methods, improving nDCG@10 by an average of 4.5% (and up to 7.8% on some datasets) by leveraging score-aware ranking, dynamic weighting, and efficient result merging.
Binary Vector Search at 350GB/s using ARM NEON
Optimizing binary vector search using ARM NEON instructions to achieve 350GB/s throughput.
TopK at Data Council AI Launchpad 2025
At Data Council 2025, we introduced TopK, a unified cloud-native query engine that combines vector search, keyword matching, and flexible scoring in a single system. We demonstrated how TopK overcomes the limitations of traditional vector databases by supporting hybrid queries with custom ranking logic while maintaining high performance.
Why Vector DBs Are the Wrong Abstraction – And What We Built Instead
We’ve spent the last three years building the most popular vector database on the market. In that time we realized that a database built around vectors as a primary key is simply the wrong abstraction, creating an unnecessary obstacle for users in production.