In “”, the authors introduce a novel multi-vector retrieval algorithm designed to bridge the efficiency gap between single- and multi-vector retrieval. They transform multi-vector retrieval into a simpler problem by constructing fixed dimensional encodings (FDEs) of queries and documents, which are single vectors whose inner product approximates multi-vector similarity, thus reducing complex multi-vector retrieval back to single-vector maximum inner product search (MIPS). This new approach allows them to leverage the highly-optimized MIPS algorithms to retrieve an initial set of candidates that can then be re-ranked with the exact multi-vector similarity, thereby enabling efficient multi-vector retrieval without sacrificing accuracy. They have provided an open-source implementation of the FDE construction algorithm on .
