Fayaz Rahman

@paultrott This happens when the file you are reading is too big, we have not yet implemented input chunking

Hey @swapneils! Thanks for the PR! We actually did have criticisms at first, but decided to remove it to keep things simpler. So let's hold off on this until we're...

@simonpfish I have updated the PR and the description, hope everything looks good now!

@simonpfish Fixed!

Hey @ChawDoe! Thanks for opening the issue. Let us look into whether any of our current workflows will satisfy your use case and we'll get back to you in a...

Sorry @ChawDoe, I haven't been able to work on this yet, I will update here as soon as I make any headway regarding this.

Hey @HyunggyuJang, thanks a lot for raising the issue. We're already working on this, and I'll be sure to let you know when the updates are released.

Hey @DocAlibi! Thank you for the PR. An issue here is that there is a loss of data when converting from float64 to 32 and we should probably not do...

This would especially be a problem if a user wants `float64` embeddings for some reason and we automatically converted it to another dtype. I can't see your example btw. I...

It would consume more storage but better to do that and print some kind of warning (that float32 is default) rather than changing input data.