THE FAISS LIBRARY

Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazare ́, Maria Lomeli, Lucas Hosseini, Herve Jegou

Penerbit : arXiv

Tahun : 2024

Vector databases typically manage large collections of embedding vectors. As AI applications are growing rapidly, the number of embeddings that need to be stored and indexed is increasing. The Faiss library is dedicated to vector similarity search, a core function ality of vector databases. Faiss is a toolkit of indexing methods and related primitives used to search, cluster, compress and transform vectors. This paper describes the trade-offs in vector search and the design princi ples of Faiss in terms of structure, approach to opti mization and interfacing. We benchmark key features of the library and discuss a few selected use cases to highlight its broad applicability.

Pengarang