feat: add bypass_n option to LangchainLLMWrapper for n-completion control #2354
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
dosubot
bot
added
the
size:XS
anistark
requested changes
Oct 12, 2025
There was a problem hiding this comment.
Thanks for the PR @SimFG
Could you please also add tests relevant to bypass_n
Add unit tests that verify:
- When
bypass_n=True, the wrapper doesn't pass n to the underlying LLM - When
bypass_n=False(default), behavior remains unchanged - Both sync (
generate_text) and async (agenerate_text) methods work correctly
Co-authored-by: Ani <5357586+anistark@users.noreply.github.com>
Add comprehensive test cases to verify the behavior of bypass_n parameter in LangchainLLMWrapper. Tests cover both sync and async methods, default behavior, and interaction with multiple completion support.
dosubot
bot
added
size:L
|
@anistark Thanks a lot for your time, I have added some relative unit test cases. |
anistark
reviewed
Oct 14, 2025
|
I have updated the pull request, thanks your careful review. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
When using some openai-compatible thinking models at that time, it was found that centain errors would occur.
2025-10-10 11:22:45,625 - ragas.executor - ERROR - Exception raised in Job[3]: BadRequestError(Error code: 400 - {'error': {'code': 'InvalidParameter', 'message': 'Reasoning model does not support n > 1, logit_bias, logprobs, top_logprobs Request id: xxx', 'param': '', 'type': 'BadRequest'}})