Issue with evaluating openai-based LLMs with mlflow.evaluate() API#1843
Merged
rabah-khalek merged 14 commits intomainfrom Mar 14, 2024
Merged
Issue with evaluating openai-based LLMs with mlflow.evaluate() API#1843rabah-khalek merged 14 commits intomainfrom
rabah-khalek merged 14 commits intomainfrom
Conversation
Hartorn
requested changes
Mar 13, 2024
| "Please submit the traceback as a GitHub issue in the following " | ||
| "repository for further assistance: https://github.com/Giskard-AI/giskard." | ||
| ) | ||
| return None, None |
Member
There was a problem hiding this comment.
Shouldn't we re raise an error ? as in perform scan ?
Contributor
Author
There was a problem hiding this comment.
No, I don't want to block the user from seing the scan results if an error occurred in the test-suite
added 3 commits
March 13, 2024 16:50
Hartorn
approved these changes
Mar 14, 2024
|
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The issue is described here: mlflow/mlflow#11266, and links to his proposals here: langchain-ai/langchain#18420 (comment).
In a nutshell, upon passing a model uri to
mlflow.evaluate(), mlflow tries to load the model, but since langchain don't yet support loading ChatOpenAI based models (the case ofRetrievalQApowered bygpt-4for instance),mlflow.evaluate()was failing.The workaround, was to avoid serializing, deserializing the langchain model, and pass a function to
mlflow.evaluate()