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

Adding evaluation to Mistral agent examples via Phoenix #107

Open
wants to merge 13 commits into
base: main
Choose a base branch
from

Conversation

Jgilhuly
Copy link
Contributor

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?

  • New Cookbook
    • Notebook File
      • Does it work on google colab?
    • Markdown File
  • Cookbook Update
    • Code Refactoring
    • Bug Fix
  • README.md Update

  • Other (please describe):

Cookbook Checklist:

  • My code is easy to read and well structured.
  • I've tagged the versions of any dependency required.
  • I have performed a self-review of my own code.
  • I have commented my code, particularly in hard-to-understand areas.
  • My changes generate no new warnings or errors.

  • My changes do not concern the cookbooks.

README.md Checklist

  • I've added my cookbook to the table.

  • My changes do not concern the README file.

Additional Context

Add any other context or screenshots about the feature request here.

...

@sophiamyang
Copy link
Collaborator

Hi @Jgilhuly thanks so much for the PR! Would it be possible for you to add new agent notebooks to the Phoenix folder? Thanks!

@Jgilhuly
Copy link
Contributor Author

@sophiamyang moved the examples over to the Phoenix folder, let me know if you had something else in mind!

@sophiamyang
Copy link
Collaborator

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?

@Jgilhuly
Copy link
Contributor Author

@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!

@sophiamyang
Copy link
Collaborator

sophiamyang commented Nov 25, 2024

Thank you @Jgilhuly ! I got few error message when running the notebooks. Could you help update please? Thank you!

  • I got error message "ImportError: llama-index-readers-file package not found" when running arize_phoenix_evaluate_rag.ipynb.
  • "NameError: name 'session' is not defined" when running arize_phoenix_tracing.ipynb code print(f"Current Phoenix URL: {session.url}")

@sophiamyang
Copy link
Collaborator

@Jgilhuly wondering if you or your team could help fix the notebooks I mentioned above. Thanks!

@Jgilhuly
Copy link
Contributor Author

Jgilhuly commented Dec 6, 2024

@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!

@sophiamyang
Copy link
Collaborator

Thank you so much @Jgilhuly! Appreciate the help!

@Jgilhuly
Copy link
Contributor Author

@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.

@sophiamyang
Copy link
Collaborator

Amazing thanks! Will take a look after the holidays and post on social.

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

Successfully merging this pull request may close these issues.

2 participants