Follow up on API design discussion for multi-partition CAGRA search
Open
Nobody has claimed this yet.
- Dominant language
- Cuda
- Stars
- 854
- Forks
- 236
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 62
Description
https://github.com/NVIDIA/cuvs/pull/2035 introduces multi-partition CAGRA search by overloading the search API in the CAGRA public header. A discussion on the PR suggests creating a new multi-partition index class that provides an abstraction for a collection of indices to be searched together:
template <typename BaseIndex>
struct multi_partition_index {
std::vector<BaseIndex> partitions;
}
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with PR #2035 and its discussion, then inspect the CAGRA public header where multi-partition search currently overloads the search API. Resolve whether a multi_partition_index abstraction should replace that design, define its expected API and behavior, and document the agreed outcome before implementation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- backend-api-design, search
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100