-
Notifications
You must be signed in to change notification settings - Fork 308
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
Adding evaluation to Mistral agent examples via Phoenix #107
base: main
Are you sure you want to change the base?
Conversation
Hi @Jgilhuly thanks so much for the PR! Would it be possible for you to add new agent notebooks to the Phoenix folder? Thanks! |
@sophiamyang moved the examples over to the Phoenix folder, let me know if you had something else in mind! |
Thank you @Jgilhuly! Is it intended you have PHOENIX_API_KEY in the notebook? Is it okay for users to use this key or would you like to remove it and delete the key? |
@sophiamyang - that key is just an example one, so fine to share. That did make me realize the notebooks were using different connection methods to phoenix - e.g. some using the hosted version and some using a local version. I switched them to be consistent, and removed the api key just to avoid confusion! |
Thank you @Jgilhuly ! I got few error message when running the notebooks. Could you help update please? Thank you!
|
@Jgilhuly wondering if you or your team could help fix the notebooks I mentioned above. Thanks! |
@sophiamyang - apologies for the delay. I fixed the bug you mentioned there, but there's an issue we still need to fix in the third_party/Phoenix/arize_phoenix_evaluate_rag.ipynb notebook to make sure our mistral eval model object is compatible with mistral>=1.0.0. I'll follow up as soon as we fix the issue, thanks for your patience here! |
Thank you so much @Jgilhuly! Appreciate the help! |
@sophiamyang - apologies for the delay, we got the update made and I've fixed the notebooks here. I also went ahead and removed one since the other agent eval notebook covered the same topics, plus more. |
Amazing thanks! Will take a look after the holidays and post on social. |
Cookbook Pull Request
Description
This PR adds tracing and evaluation walkthroughs to two of the Mistral agent examples. The changes are contained to optional sections at the end of the two notebooks, and give a comprehensive demo of how the Agents can be evaluating using Phoenix
...
Type of Change
What type of PR is it?
Cookbook Checklist:
README.md Checklist
Additional Context
Add any other context or screenshots about the feature request here.
...