Skip to content
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

chore: use chunk data in NIAH and QA evals #1067

Closed
jalling97 opened this issue Sep 18, 2024 · 0 comments · Fixed by #1176
Closed

chore: use chunk data in NIAH and QA evals #1067

jalling97 opened this issue Sep 18, 2024 · 0 comments · Fixed by #1176

Comments

@jalling97
Copy link
Contributor

Describe what should be investigated or refactored

At the moment, no chunk data is used in evaluating the two major evaluations present in LFAI evals. At the moment, proxies have to be used using the annotations. This is because it is not returned as part of the OpenAI spec. After LFAI annotations are upgraded to include this info, the chunk data can be used to make better evals.

Additional context

Blocked by: #870

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant