Support predicted output in DSPy #8247
Merged
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
okhat
reviewed
May 20, 2025
| @@ -108,6 +108,17 @@ def _forward_preprocess(self, **kwargs): | |||
| if (temperature is None or temperature <= 0.15) and num_generations > 1: | |||
| config["temperature"] = 0.7 | |||
|
|
|||
| if "prediction" in kwargs: | |||
| if ( | |||
There was a problem hiding this comment.
Happy to merge for now but:
-
Should we just check (or maybe also check?) whether
predictionis a key in the signature? -
I suppose the cleanest way for this would have been to make it a new type and handle it in adapters 😅 But this would start to feel like too many types...
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Outdated suggestions cannot be applied.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.
Support the predicted output feature: https://platform.openai.com/docs/guides/predicted-outputs. The implementation is based on litellm's predicted output: https://github.com/chenmoneygithub/dspy
To avoid the edge case that user input field has
prediction, I am adding a check on the format ofprediction, and only when it's a valid predicted output format, I am piping it to the LM call kwargs.