ann-benchmarks
ann-benchmarks copied to clipboard
erikbern
Benchmarks of approximate nearest neighbor libraries in Python
Would it be in the spirit of this benchmarks to add a second benchmark category for ANN in conjunction with categorial filters? Most real-world applications of ANN will required category...
Hi! I am following every step of the instruction and install.py shows that all the algorithms are installed success. But when I run on glove there is an internal server...
Firstly, thank you very much for creating this benchmark. It is very helpful for navigating this exciting but somewhat overwhelming field. I am interested in particular in the performance of...
I was wondering if there is a way of defining what is a “reasonable” relative error, something similar to recall 0.9, 0.95, 0.99. Furthermore, how much is this metric is...
Hello, I've followed these [instructions ](https://github.com/erikbern/ann-benchmarks#running). I wanted to quickly evaluate the algorithms on a single dataset via ```python run.py --dataset glove-25-angular```. However, I get the following errors for ```Elasticsearch```,...
this PR introduces the ability to export results into a json file
This was recently released in Elasticsearch 8.0+ and the API is documented [here](https://www.elastic.co/guide/en/elasticsearch/reference/current/knn-search-api.html) Elasticsearch is distinct in both implementation and product from OpenSearch (Amazon maintained fork), and I expect that...
I've been working on benchmarking pynndescent on other metrics such as Jaccard, and have been using ``ann-benchmarks`` and the ``kosarak`` dataset for that. Some recent PRs (#235 and #238) have...
Hi, Thanks for the great work ! I found out TorchPQ recently : https://github.com/DeMoriarty/TorchPQ > TorchPQ is a python library for Approximate Nearest Neighbor Search (ANNS) and Maximum Inner Product...
hi, i found the diskann algorithm docker images can't be generated for follow issue. it seems MKL lib accessing issue. Step 1/24 : FROM ann-benchmarks ---> 24a97f036f16 Step 2/24 :...
