Andrey Vasnetsov

Hey @azeng528, it is not enough information to reproduce the problem you are reporting. We would need to know: - full collection info you configured - exact queries you are...

usually we recommend to use proper vector database

For reference, our benchmark of fastembed is here - https://colab.research.google.com/github/qdrant/fastembed/blob/main/experiments/Throughput_Across_Models.ipynb I would have to try your version to tell for sure what's the difference, but at the first glance you...

Thanks for sharing, we will look into it!

@0110G Refactored the testing script a bit, here are my results: https://colab.research.google.com/drive/1SroKOUZ0iYN1vo2mRXdhIQeVyy0RWQTG?usp=sharing It uses internal batching instead of external loop, as both libraries actually provide the interface capable of creating...

@0110G I think I understood the problem: when you call `embed` function in fastembed, it spawns workers each time. So, it would create an overhead. I tried to convert fastembed...

I was running colab on a higher tier machine with 8cpu, it might be the reason

Write operation support is quite limited and might be confusing if applied without checking on the documentation. I would prefer to keep it as-is for now

~it is necessary~ we need to check

Hey @JINO-ROHIT, if you compute the metric values manually, which version does it match?