AsyncLM #2004
Open
AsyncLM #2004
+546
−21
Conversation
This file contains 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
Goldziher
reviewed
Jan 4, 2025
| from dspy.utils import with_callbacks | ||
|
|
||
|
|
||
| class AsyncLM(LM): |
Goldziher
reviewed
Jan 4, 2025
|
|
||
| class AsyncLM(LM): | ||
| @with_callbacks | ||
| def __call__(self, prompt=None, messages=None, **kwargs) -> Awaitable: |
There was a problem hiding this comment.
This should be async to allow for the caller to use this in an async fashion, no?
async def __call__(...)
There was a problem hiding this comment.
Yup, and callbacks should be handled async. Check out #1734 if you need something that works for you in the meantime
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Outdated suggestions cannot be applied.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.
Hey @okhat, thanks for this repository its really super.
One step towards proper async functionality is having an
AsyncLM, similar to how OpenAI has their Client and AsyncClient.I know this PR has some code duplication issues, however I think its better to have a separate async LM rather than handling both sync and async in the
LM's__call__.This PR complements #1988 and lays a foundation for async modules to use async lm client