lucene icon indicating copy to clipboard operation
lucene copied to clipboard

Multi-value Support for KnnVectorField

Open alessandrobenedetti opened this issue 1 year ago • 21 comments

Description

It would be nice to support multiple values in a Knn vector field. This must be compatible with both the Exact and Approximate Nearest Neighbor search.

There are two sides to the coin:

  1. Index time support - allowing to add in the indexing data structures multiple vectors for the same field and docID
  2. Query time support - how to retrieve a topK list of documents, where each document my have multiple neighbors to the query

The problem is more complicated than it seems.

An initial tentative design and draft implementation is attached

alessandrobenedetti avatar May 19 '23 15:05 alessandrobenedetti