meilisearch / meilisearch/arroy

submit arroy to ann-benchmarks

Open
#142 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Rust
Stars
311
Forks
17
PR merge metrics
No merged PRs in 30d

Description

ann-benchmarks is a benchmarking environment for ann implementations written in Python by the same guy who did annoy.

It would be cool to submit arroy there to see how it compares to other implementations (qdrant, weaviate, milvus, etc), most of which are are hnsw-based (side note: i think an lmdb-based hnsw implementation would be sick).

This can be accomplished by :

  • using the python bindings once completed
  • using a client-server approach like with tonic and performing indexing/search through RPCs (this is what qdrant did)

It would also be cool to see how arroy compares to annoy, tying in nicely to #17 maybe

Image

Contributor guide

No contributing guide indexed for this repository

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 Python bindings referenced in PR #133 and the integration requirements for ann-benchmarks. Compare the bindings route with the tonic client-server approach, then choose one submission path and include arroy in the ann-benchmarks comparison with annoy. Done means arroy runs in the benchmark suite and produces comparable results.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, rust
Domain
machine-learning, testing
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.