Software Engineer
Ilya Kuznetsov is a Software Engineer and author of Manticore Search publications on hybrid search and KNN prefiltering.
See how memory-mapped database files make columnar KNN rescoring in Manticore Search 2.57–3.13x faster without slowing out-of-core search.
A head-to-head benchmark on 975K 1536-dim vectors: turbopuffer's managed service vs Manticore on two $8.25/mo VPS. Matched recall (~0.966), ~4.5× lower cost, and comparable latency and throughput, with an honest look at where each approach wins.
Manticore can now build KNN indexes in parallel when saving chunks, merging chunks, and rebuilding KNN data. On a 16-core machine, building a KNN index for 1M vectors dropped from 8 minutes to 39 seconds.
Three optimizations that speed up HNSW vector search by up to 29%: restructured graph traversal for better cache utilization, batched distance computations, and AVX-512 support.
How Manticore detects when HNSW search has converged and stops early, cutting distance computations by 50-80% with minimal precision loss.
Explains how KNN prefiltering in Manticore applies attribute filters during vector search, when ACORN-1 and brute-force fallback kick in, and when postfiltering is still preferable.
Combine full-text and vector search in Manticore using Reciprocal Rank Fusion (RRF) to get more precise results than either method alone.
Install Manticore Search in one command on Linux or macOS:
curl https://manticoresearch.com | sh
For advanced installation options, see the full installation guide and the manual .