-
Notifications
You must be signed in to change notification settings - Fork 48
feat!: add structured output for ai map, ai filter and ai join #1746
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
Conversation
The change only breaks pre-release features, so please add a |
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.
LGTM overall, with leaving two comments.
@@ -244,8 +301,8 @@ def test_map_multimodel(session, gemini_flash_model): | |||
) | |||
result = df.ai.map( |
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.
nit: assert the results' columns are expected?
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.
I would refrain from doing that because the answer is not stable.
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
BEGIN_COMMIT_OVERRIDE
feat!: add structured output for ai map, ai filter and ai join (#1746)
The metric shows that there are no recent external calls to our ai operators, this change should be safe.
Also added:
logprob
will be available as an output if the user wants to check them.BREAKING CHANGE: the updated
ai.map()
parameter list is not backward-compatibleRelease-As: 2.5.0
END_COMMIT_OVERRIDE