Ruben Bridgewater
Ruben Bridgewater
The branch has a couple of conflicts at the moment that would have to be resolved, though. The overall size is also difficult to review everything.
> It seems, this PR is 15% faster That only applies to the non-existing part. The question for me is what is more likely: existing or non-existing? ``` confidence improvement...
@RedYetiDev do you have some screenshots or a short video of the usage? I am not certain in what way the syntax highlighting has changed :)
Was there any update on this @AlanSl? And are we not already using `trace_events`? I am pretty sure we use them in `Bubbleprof`.
@AndreasMadsen in that case this should be closed, right?
The benchmark suite does not yet seem to accept this as is
+1 to disable discussions
I just had a brief look and it seems to me this would need to be reworked from scratch, since we implemented langchain support by now, just without the iast...
I'll wait until Friday this week and land it as is in case there is no further review until then.
It would probably be good to always include the current limit in the error message. We might want to look into the actual reason for the original limit. It could...