5 papers
Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings
Leonardo Kuffo, Peter Boncz
In this study, we revisit three widely used techniques in vector search and utilize them to optimize vector embedding indexing through clustering: dimensionality reduction, quantiz…
Semantic Recall for Vector Search
Leonardo Kuffo, Ioanna Tsakalidou, Roberta De Viti +3
We introduce Semantic Recall, a novel metric to assess the quality of approximate nearest neighbor search algorithms by considering only semantically relevant objects that are theo…
A Super Fast K-means for Indexing Vector Embeddings
Leonardo Kuffo, Sven Hepkema, Peter Boncz
We present SuperKMeans: a k-means variant designed for clustering collections of high-dimensional vector embeddings. SuperKMeans' clustering is up to 7x faster than FAISS and Sciki…
Bang for the Buck: Vector Search on Cloud CPUs
Leonardo Kuffo, Peter Boncz
Vector databases have emerged as a new type of systems that support efficient querying of high-dimensional vectors. Many of these offer their database as a service in the cloud. Ho…
PDX: A Data Layout for Vector Similarity Search
Leonardo Kuffo, Elena Krippner, Peter Boncz
We propose Partition Dimensions Across (PDX), a data layout for vectors (e.g., embeddings) that, similar to PAX [6], stores multiple vectors in one block, using a vertical layout f…