Jon Bratseth
Jon Bratseth
It's still marked for "later". I'll reset so we retriage. You could add any information relevant to prioritizing this.
The Vespa core work needed is expert level so probably not suitable for external contributions (although you're welcome to assess this yourself - code and build instructions are on GitHub)....
Agreed - thanks!
I feel supporting string matching operations on structured keys is a road we might not want to go down ... If we supported indexing with multiple mapped dimensions, could you...
Those researchers keep messing up our simple and clean design :sob: I think the best way to solve this on the IL side is to cache the outputs behind the...
That will only work if all the representations have the same type though.
This could be improved, but that is not always the goal, or the only goal; any output from a function (/model) can be added to the returned result, whether or...
I think we want to stick with a curated set with a guaranteed lifecycle: https://cloud.vespa.ai/en/model-hub
In development.
The grouping result is generated from the matches. If you want to generate a grouping result covering the complete universe of possible choices you can do that by sending another...