-
Notifications
You must be signed in to change notification settings - Fork 112
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
RAGAS error #70
Comments
Hi @ibagur can you please share the snippet from the log where it prints the |
Hi @aravind10x , I rebuilt the Docker image and run another test. The synthetic data was generated, but I got several errors when running the whole process. This time I kept the whole log, which I paste here. I did not use a very complex set of settings, and only 10 runs of Bayesian optimization.
|
Hi @aravind10x
|
@ibagur @sanidhyabitcot - will look into this and get back asap. Working on an improved SDK version of this which will ideally eliminate this issue. |
I am running
ragbuilder
on MacOS 14.6.1, built from the Docker image and run as a container. I have followed the 'Getting started' example using the provided blogpost and also a small set of selected parameters for a quicker run. I have tried with both OpenAI models (gpt3.5-turbo and gpt-4o-mini) but also with local Ollama models. At some point, after embeddings get created and synthetic data starts being generated, the script always rises an error before completing the process, apparently related to a RAGAS issue.I am not too familiar with RAGAS framework, so I have not tried to debug it myself for the moment. I paste here the error log, in case any one can shed some light:
The text was updated successfully, but these errors were encountered: