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

A reminder for the frequent error regarding openai_key in the evaluate #1781

Closed
wants to merge 2 commits into from

Conversation

WKRZY
Copy link

@WKRZY WKRZY commented Dec 20, 2024

During the invocation of the evaluate function, I observed a common issue: when users do not pass in their custom LLM (Large Language Model), the function automatically attempts to call OpenAI's model. However, if the user has not set the OPENAI_API_KEY environment variable at this point, it will cause the function to fail and throw an error. To address this problem and enhance user experience, I have introduced a new feature to remind users to set their API key.

@dosubot dosubot bot added the size:S This PR changes 10-29 lines, ignoring generated files. label Dec 20, 2024
@jjmachan
Copy link
Member

jjmachan commented Jan 3, 2025

hey @WKRZY
Firstly thank you so much for taking the time to improve the Ragas for everyone. we really appreciate that ❤️

but unfortunatly this is not the solution that solves the root cause which is useing openAI as default and the users not knowing this. This was a result of a design decision we had made and will be fixing it in #1558 but we have not merged it since it's breaking and waiting for v0.3

let me know if you have any questions, if not can I close this?

thanks again for your effort 🙂

@WKRZY WKRZY closed this Jan 5, 2025
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.

2 participants