TusKANNy

Modular and Efficient Approximate Nearest Neighbors Search with Vectorium and kANNolo @SilvioMartinico et al. present two Rust libraries for nearest neighbor search over dense, sparse, and multi-vector embeddings. 📝 arxiv.org 👨🏽‍💻 github.com/TusKANNy/papers_reproducibility/tree/m…

Modular and Efficient Approximate Nearest Neighbors Search with Vectorium and kANNolo Presents two Rust libraries for nearest neighbor search over dense, sparse, and multi-vector embeddings, with swappable components. 📝 arxiv.org 👨🏽‍💻 TusKANNy/kannolo

Modular and Efficient Approximate Nearest Neighbors Search with Vectorium and kANNolo Approximate Nearest Neighbors (ANN) search over neural embeddings powers modern retrieval systems such as Retrieval-Augmented Generation. Embeddings come in three representations (dense, sparse and multi-vector), and efficient search combines an index structure, a similarity function and a quantization scheme. Existing libraries fix one combination, hard-code each one separately, or factor only one side of the problem, and none covers all three representations. We present Vectorium and kANNolo, two open-source Rust libraries that split this design space into a data-management layer and an indexing layer. Vectorium abstracts the vector, the distance function, the quantizer and the dataset independently, and provides 11 encoders, from 32-bit floats to sub-bit codes. On top of it, kANNolo implements Hierarchical Navigable Small-World (HNSW) graph and Inverted Vector File (IVF) indexes that are generic over representation, encoder and metric, and a two-stage index that composes any first-stage index with any rescoring dataset. Since every combination is specialized at compile time, this modularity adds no run-time overhead, and the resulting indexes reach state-of-the-art performance: our Product Quantization matches Faiss in accuracy at competitive speed, our RaBitQ and HNSW match or outperform their reference implementations, and our IVF outperforms Faiss. Against six dense and five sparse systems on seven public collections, our indexes give the best memory-throughput trade-off on dense data in 9 of 12 collection-accuracy pairs and perform well on out-of-distribution queries. On sparse data, the systems built on Vectorium lead on all three collections, with Seismic and SeismicWave the fastest and kANNolo's indexes the most compact. Comments: 39 pages, 11 figures, 17 tables. Submitted to Information Systems. Code and data: github.com/TusKANNy/papers_reproducibility/tree/m…

Lossless Compression of Proximity Graph Indexes for Efficient Approximate Nearest Neighbors Search Compresses HNSW edge lists by reordering node IDs offline and using fast SIMD integer codecs, cutting memory. 📝 arxiv.org 👨🏽‍💻 github.com/tusKANNy/papers_reproducibility/tree/m…

Lossless Compression of Proximity Graph Indexes for Efficient Approximate Nearest Neighbors Search Graph-based Approximate Nearest Neighbor (ANN) indexes, such as HNSW, are the backbone of modern vector search. However, their massive memory footprint creates a severe infrastructure bottleneck. While vector quantization is widely adopted to reduce the memory required to store data vectors, the graph's edge structure increasingly dominates total memory usage. Compressing these adjacency lists for online search presents a critical system challenge: because decompression occurs during query processing, i.e., while navigating the graph, memory savings cannot come at the expense of query latency. In this paper, we present a compression technique explicitly tailored for live HNSW routing. By applying offline graph permutations to artificially induce structural locality, we enable the use of SIMD-accelerated integer compressors, such as Stream VByte, for rapid on-the-fly decompression. Evaluated across diverse real-world workloads, we significantly outperform the current state of the art in both compression ratio and query latency. Our experimental results show that we achieve compression ratios up to 52.7% with negligible penalties in latency compared to the uncompressed baseline. Furthermore, our technique has been effectively deployed in production at eBay, achieving up to 44.3% reduction in edge storage with no degradation in query latency. Comments: 7 pages, 5 figures, Accepted at CIKM 2026. Code: TusKANNy/kannolo. Reproducibility: github.com/tusKANNy/papers_reproducibility/tree/m…