-
Notifications
You must be signed in to change notification settings - Fork 77
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
fix: DIA-1489: Multiskill prompt autorefinement fixes #237
Conversation
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #237 +/- ##
==========================================
- Coverage 65.89% 65.67% -0.22%
==========================================
Files 47 47
Lines 2372 2389 +17
==========================================
+ Hits 1563 1569 +6
- Misses 809 820 +11 ☔ View full report in Codecov by Sentry. |
if reapply: | ||
predictions = await self.skills.aapply(inputs, runtime=runtime) | ||
else: | ||
predictions = inputs |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
in the future, it should be possible to automatically detect if predictions are missing and aapply in that case, and get rid of this reapply
arg, right?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
actually it doesn't seem clear to me whether predictions must be applied or not. However, the performance/cost implications are clear. So I'd leave this option for now and put off to decide on the best setup later when we will have some benchmarks to understand the quality tradeoff.
adala/skills/_base.py
Outdated
.str.cat(sep=self.input_separator) | ||
) | ||
|
||
chunk.to_csv('chunk.csv', index=False) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What is this for? debug left in?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
oops, debuging stuff
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
fixed
Hi @niklub!
This PR was automaticaly generated via Follow Merge.
Please ensure that all linked upstream Pull Requests are merged before proceeding with this one.