Skip to content

Conversation

ziggycross
Copy link

Description

Closes #1990 by adding type checks and improved error handling. This issue was a bit unintuitive when I came across it, and is easily fixed by having a more descriptive error message.

Changes Made

Added type checks in the evaluate function which validate the metrics arguments.
I also noticed a missing step in the development instructions so fixed that while I was there.

@dosubot dosubot bot added the size:S This PR changes 10-29 lines, ignoring generated files. label Apr 16, 2025
@@ -65,6 +65,11 @@ make run-ci V=1

## Running Tests

To install the libraries required for testing:
```bash
pip install -e ".[test]"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not sure if this is adding any value.

Should be handled with uv sync --group dev

@anistark
Copy link
Contributor

Thanks for the PR @ziggycross
Could you please rebase and check for the merge conflict?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
size:S This PR changes 10-29 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

AttributeError when I try to use ContextRelevance, LLMContextPrecisionWithoutReference to evaluate the test dataset
2 participants