microsoft / microsoft/DiskANN

Fix recall and perf issues in Determinant Diversity algo

Open
#1,197 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Rust
Stars
1.9k
Forks
454
Avg merge
3d 22h
Merged PRs (30d)
35

Description

**Status as of Sep 10, 2026:**
Determinant diversity algo is already present in main branch. The algorithm is integrated with bechmarks. But the algorithm is inefficient. Kiran is working on better implementation of the algorithm. Once it is ready, it needs to be integrated into the code. This PR has a slightly better algorithm implementation and needs to be replaced with final version from KIran.

https://github.com/microsoft/DiskANN/pull/1249 draft PR covers this partially completed work.

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 existing determinant diversity algorithm in the main branch and the partially completed draft PR #1249. Compare that implementation with Kiran's planned final version, then integrate the replacement and verify the existing benchmarks cover recall and performance improvements.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
performance, search
Issue type
Refactor
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.