Flatten messages by default, except if image found in messages #1002
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@albertvillanova would be interested to hear your thoughts on this change! |
There was a problem hiding this comment.
Before going into the details, just a general thought: you introduced a breaking change. Previous code where users have explicitly set a boolean value for flatten_messages_as_text will fail after merging this PR.
Maybe introducing a new parameter for the transition/deprecation? Also note that I find the current variable name flatten_messages_as_text a little confusing... So this could be the opportunity to introduce another parameter.
|
The naming confusion I mentioned before is because we are flattening message content, not the messages themselves. Some random ideas about naming:
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In our
Modelsubclasses,flatten_messages_as_textactually should allow three values to adapt to the idiosyncracies of different APIs: 'never', 'auto' (flatten if possible, i.e. if messages don't contain any image), and 'always'.