Reproducibility

[slice4e]

Thank you for a great work.
I would like to reproduce the results and compare to another engine. Following the documentation, it appears that you have already included a test in ann-benchmarks:

The code to run OG-LVQ can be found here, and it was included in the ANN-benchmarks and Big-ANN-benchmarks evaluation codes following their guidelines.

Unfortunately, I am not able to find it. Could you please provide a link?

thank you

[marianotepper]

Thank you for your interest!

For our results, we made internal forks of the ANN-benchmarks and Big-ANN-benchmarks frameworks, as we collect more metrics than those in the original versions. As these forks are not part of SVS proper, we never got to release them. We're working on releasing sample code for the integration with these frameworks.

[akashsha1]

+1 My team would also be interested when you release code for the integration with ANN-benchmarks framework.

[mihaic]

I am working on releasing the integration code. I will update this issue as I make progress.

[napetrov]

https://github.com/intellabs/ScalableVectorSearchBenchmarking - this is public version of benchmarks scripts that can be used for reproducing results.