ann-benchmarks
ann-benchmarks copied to clipboard
erikbern
Benchmarks of approximate nearest neighbor libraries in Python
Opening new issue as: Any pointer what is wrong and what code should be used to connect Milvus database with connection info ? ~/ann-benchmarks$ sudo python3 run.py --dataset glove-25-angular --algorithm...
It'd be useful to provide csvs in the results folder with the raw data in tabular form for each plot. This would make it easier to modify the plots, e.g....
Algo updates
I'm planning to re-run all benchmarks shortly. Going through the algos with some todos (checking boxes as I fix it) Currently failing in CI: * [X] diskann – something with...
This PR makes it possible to specify custom runners to run ann-benchmarks in containerized, non-Docker environments. My use case is that I (and many others) have to use SLURM on...
https://solr.apache.org/guide/solr/latest/query-guide/dense-vector-search.html new HNSW implementation in Solr9
https://github.com/erikbern/ann-benchmarks/blob/1bf6cfd15ab410c2059ab277c1ee1c1fe85f51fe/ann_benchmarks/algorithms/faiss/config.yml#L42 Is `1204` correct, or should it be `1024`?
Hey @erikbern and ANN Benchmarking team! Thanks for creating and maintaining a clean and sophisticated repository for the community. I am Anubhav, an NLP Researcher at Advanced Symbolics Inc. Me...
This project is awesome and great but I was wondering couldn't you also provide a table with final rankings? Use whatever criteria you like but would be good to have...
I am trying to build a docker image for the `scann` algorithm like this on a **Mac**: ``` % docker build . -f ann_benchmarks/algorithms/scann/Dockerfile -t ann-benchmarks/scann ``` I understand the...
In theory, if a system has a latency of 1 millisecond for a request, one might think the system can handle 1000 (1/0.001) requests per second, implying a direct correlation...
