ann-benchmarks
ann-benchmarks copied to clipboard
erikbern
Benchmarks of approximate nearest neighbor libraries in Python
Dear Ann-benchmark team, I am wondering whether the recently developed FlatNav (https://github.com/BlaiseMuhirwa/flatnav, paper here: https://arxiv.org/abs/2412.01940) or simple HubNSW, which use hubs in the dataset instead of hierarchy to guide navigation....
Hi, I am filing this issue to propose simplifying ann_benchmarks by maintaining only one mode instead of the current single and batch modes and presenting unified benchmarking results independent of...
Currently, `ANN-Benchmarks` enforces single-CPU execution during experimentation, disabling multi-threading capabilities at the hardware level (AWS single-cpu mode) so that even libraries supporting multi-core CPU/threading can't use it. While batch mode...
``` (base) jiangyinzuo@kiwi:/usr3/jiangyinzuo_data/ann-benchmarks$ python3 create_dataset.py --dataset nytimes-256-angular building matrix... normalizing matrix entries with tfidf... reducing dimensionality... Splitting 300000*None into train/test train size: 290000 * 256 test size: 10000 * 256...
``` DATASETS: Dict[str, Callable[[str], None]] = { "deep-image-96-angular": deep_image, "fashion-mnist-784-euclidean": fashion_mnist, "gist-960-euclidean": gist, "glove-25-angular": lambda out_fn: glove(out_fn, 25), "glove-50-angular": lambda out_fn: glove(out_fn, 50), "glove-100-angular": lambda out_fn: glove(out_fn, 100), "glove-200-angular": lambda...
1. I saw from the official website that the latest results available are from 2023. I would like to ask if there are any plans to update the latest evaluation...
I like to suggest the following enhancements 1) Select/Unselect All Plots Add an option to easily select or unselect all plots at once. This will allow users to start with...
JVector is available [here](https://github.com/jbellis/jvector) and it would be awesome to have it in the benchmark comparisons. This library powers some of the famours vector databases out there such as but...
