Billion-scale Similarity Search Using a Hybrid Indexing Approach with Advanced Filtering
arXiv:2501.13442 · doi:10.2478/cait-2024-0035
Abstract
This paper presents a novel approach for similarity search with complex filtering capabilities on billion-scale datasets, optimized for CPU inference. Our method extends the classical IVF-Flat index structure to integrate multi-dimensional filters. The proposed algorithm combines dense embeddings with discrete filtering attributes, enabling fast retrieval in high-dimensional spaces. Designed specifically for CPU-based systems, our disk-based approach offers a cost-effective solution for large-scale similarity search. We demonstrate the effectiveness of our method through a case study, showcasing its potential for various practical uses.
14 pages, 3 figures, published in Cybernetics and Information Technologies