NVIDIA / NVIDIA/cuvs

[FEA] `cuvs::neighbors::index` to define common methods and arguments

Open
#165 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

Currently, we define a common base class for the knn/ann index but we don't yet define standardized methods / arguments for build, search, and extend. We should define these and make sure the APIs are all consistent across all algos.

The benefit to this is polymorphism, which allows us to start creating higher-level APIs like tiered index and multi-gpu capabilities that only rely on the index, without regard to the type of index.

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 reviewing the common base class for the knn/ann index and comparing the existing build, search, and extend APIs across all algorithms. Done means these methods and arguments are standardized consistently enough to support polymorphic higher-level APIs such as tiered index and multi-GPU capabilities.

Written by the indexing model from the issue text.

Assessment

Domain
backend-api-design, search
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.