Jeff Huber
Jeff Huber
Our underlying impl has changed and so this PR is not landable as is. That being said - we'd still like to add this functionality and that is now tracked...
Our underlying impl has changed and so this PR is not landable as is. That being said - we'd still like to add this functionality and that is now tracked...
@eebmagic can you tell me more about your use case? and the motivations behind this? we have thought about this but currently don't have a super clean way of doing...
@eebmagic can you tell me more about your use case? and the motivations behind this? we have thought about this but currently don't have a super clean way of doing...
@eebmagic currently our recommended path here is to write a small util to manage the "duplicated" index. should be pretty easy - ofc a bit less efficient to store the...
@lironrisk there are many edge cases here which is why we try to "stay out of it" - the `reset` flow works... you could also consider making your `ids` "mean"...
closing in favor of https://github.com/chroma-core/chroma/issues/1330 - thanks for requesting this!
@kkollsga the way we want to solve this is by adding indexes to metadata. Post-filtering will cause very strange behavior because you will have to massively "over-retrieve" and then possibly...
@benjreinhart ah! that has been fixed now https://github.com/chroma-core/chroma/pull/929 - i will cut a new release of the `npm` package later today.