Andrew Kane

@aytekinar No need to do anything with the PR. Will add the other distance functions, and include you as a co-author when merging (thanks for the idea and all of...

Added CPU dispatching for `halfvec` distance functions in the commit above (likely still needs a few tweaks). @aytekinar, added you as a co-author since your work in this PR was...

Added CPU dispatching for key vector distance functions in the commit above. A few findings: 1. `arch=x86-64-v*` [isn't available](https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101696) with GCC < 12 2. function multiversioning is [in beta on...

Hi @knizhnik, thanks for the PR. It's an interesting approach, but want to explore potentially more efficient methods like [HQANN](https://arxiv.org/abs/2207.07940) for filtered search. For returning results out-of-order: It's definitely not...

Thanks for the feedback. @jkatz The issue with low selectivity using a vector index is the query will likely return few or no results, which happens now (#263). Also, HQANN...

Apart from the specific implementation, I'd be curious to hear thoughts on whether the test cases make sense. For instance, does it make sense to use an index for the...

> I'm not sure if measuring on selectivity alone will account for this. For example, a selectivity of 0.05 on a dataset of 100K has a far higher chance of...

Hey @hlinnaka, thanks for more PRs! I'm currently working on in-memory parallel index builds, but will dig into this and #388 once that's finished (as it may affect the impact...

Thanks @hlinnaka. Looking at the test failures across multiple CI runs, I'm not very confident this doesn't introduce a bug (but don't immediately see what it is).

I think the issue is `wdoff` isn't incremented after the last iteration. A possible fix would be: ```c while (wdoff < wdlen && list_length(r) < lm) r = lappend(r, wd[wdoff++]);...