Replies: 1 comment 2 replies
-
No, it is just an overlook. Fancy a PR?
…On Wed 8 Jan 2025 at 16:58, Diego Ramp ***@***.***> wrote:
Thanks for
https://docs.quarkiverse.io/quarkus-langchain4j/dev/testing.html
What i miss though is having the "actual response" in the evaluation
result.
This would be quite handy when evaluating/tuning to know why specific
evaluation is KO.
Of course we can log it somehow but i think it should at least optionally
be available.
was it an explicit decision to not provide it may be because of
memory-consumption or such?
what do you think?
@cescoffier <https://github.com/cescoffier>
—
Reply to this email directly, view it on GitHub
<#1206>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/AADCG7OGWI6LVCPQHYLIUR32JVDJTAVCNFSM6AAAAABU2HXIQOVHI2DSMVQWIX3LMV43ERDJONRXK43TNFXW4OZXG44TQMZTGE>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Thanks for https://docs.quarkiverse.io/quarkus-langchain4j/dev/testing.html
What i miss though is having the "actual response" in the evaluation result.
This would be quite handy when evaluating/tuning to know why specific evaluation is
KO
.Of course we can log it somehow but i think it should at least optionally be available.
was it an explicit decision to not provide it may be because of memory-consumption or such?
what do you think?
@cescoffier
Beta Was this translation helpful? Give feedback.
All reactions