-
Notifications
You must be signed in to change notification settings - Fork 11
!feat: Support multiple completions in backends #48
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
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
Generate multiple completions for a single prompt by adding the num_return_sequences parameter. This has limited support by the providers. The parameter for the providers can have different names and may require a 2nd parameter is also used. The changing of results returned to be a list is a breaking change. Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
* Only test_backends.py for now * Adding recorded cassettes (manual/default) * By default, record mode is none. So tests use cassettes, but fail if more are needed. Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
* notebook install is smaller than full jupyter * Going back to running command instead of leveraging tox to try to avoid running out of space (faster would be nice too) Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
* Pin to older vcrpy to avoid flakey httpx.ResponseNotRead * Added retry as well, but those might not be needed anymore (we'll see) * Added tox -e record (to rewrite recordings and self doc) * Added block-network settings to help ensure recordings are used Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
frreiss
approved these changes
Mar 6, 2025
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
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.
Generate multiple completions for a single prompt by adding the num_return_sequences parameter.
This has limited support by the providers. The parameter for the providers can have different names and may require a 2nd parameter is also used.
The changing of results returned to be a list is a breaking change.
Closes: #37