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