Leland McInnes
Leland McInnes
I agree this is odd, and I'll try to keep a lookout for a reproducer.
So it was quirky. There was some code added to bail when the tree splitting was not working well and avoid excess depth. Unfortunately that meant that, in rare cases,...
That seems not good ... I'll try to check this when I get some time.
Thanks @jakobhansen-blai I'll try to get a new release out tomorrow to fix this.
For such a large k, yes, there is going to be some potential benefit to building with a decently large k to ensure a quality index, and then querying. I...
No, I think you are correct. This should probably be fine for large indices, but when you get low in the tree perhaps it could actually come into play? Thanks...
Thanks, I'll try to look into this when I get a chance.
I would love a sematic search example for the docs; I don't have time right now to get it done, so a PR would be greatly appreciated.
So the bad news is that distances calculated during the search are thrown away to save memory, so they just aren't accessible as you would want. The possibly good news...
If I understand you correctly you want essentially an "out-of-core" fit method that doesn't require the whole dataset to be in memory at one time? I believe that this is...