NVIDIA / NVIDIA/cuvs

[FEA] Support multi-vector lookup

Open
#1,191 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request
Dominant language
Cuda
Stars
854
Forks
236
Avg merge
3d 3h
Merged PRs (30d)
62

Description

We need to find a good strategy for multi-vector retrieval. Chamfer distance (#1190) might be a good option. Vespa (and many other databases) use MaxSim. We should look info these approaches and see what might make the most sense.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading issue #1190 and reviewing the Chamfer-distance and MaxSim approaches mentioned in this issue. Compare their suitability for multi-vector retrieval in cuVS, then document a concrete recommended direction and the implementation scope that would count as done.

Written by the indexing model from the issue text.

Assessment

Domain
search
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.