Skip to content

Port to gpt-4o-mini as default #2443

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

Merged
merged 4 commits into from
Mar 24, 2025
Merged

Conversation

pamelafox
Copy link
Collaborator

@pamelafox pamelafox commented Mar 22, 2025

Purpose

This PR upgrades to gpt-4o-mini as the default chat completion model.
See my analysis here:
https://blog.pamelafox.org/2025/03/gpt-4o-mini-vs-gpt-35-turbo-for-rag.html
The responses are longer, but it should be overall cheaper,
and it's a more recent model.

Does this introduce a breaking change?

When developers merge from main and run the server, azd up, or azd deploy, will this produce an error?
If you're not sure, try it out on an old environment.

[X] Yes - With existing environments, it will keep gpt-35-turbo
[ ] No

Does this require changes to learn.microsoft.com docs?

This repository is referenced by this tutorial
which includes deployment, settings and usage instructions. If text or screenshot need to change in the tutorial,
check the box below and notify the tutorial author. A Microsoft employee can do this for you if you're an external contributor.

[X] Yes - Maybe? It might mention the model
[ ] No

Type of change

[ ] Bugfix
[ ] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[X] Other... Please describe:

Code quality checklist

See CONTRIBUTING.md for more details.

  • The current tests all pass (python -m pytest).
  • I added tests that prove my fix is effective or that my feature works
  • I ran python -m pytest --cov to verify 100% coverage of added lines
  • I ran python -m mypy to check for type errors
  • I either used the pre-commit hooks or ran ruff and black manually on my code.

@@ -2,26 +2,26 @@
"gpt_groundedness": {
"pass_count": 49,
"pass_rate": 0.98,
"mean_rating": 4.94
Copy link
Collaborator

@mattgotteiner mattgotteiner Mar 22, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In a future PR - we may want to add an additional set of prompts for each version of the model

@pamelafox pamelafox marked this pull request as ready for review March 24, 2025 21:07
@pamelafox
Copy link
Collaborator Author

I have done a test azd up with my old environment and a brand new environment, all seems well. Merging.

@pamelafox pamelafox merged commit 236b592 into Azure-Samples:main Mar 24, 2025
18 checks passed
@pamelafox pamelafox deleted the gpt4omini branch March 24, 2025 23:34
@Jbrocket
Copy link

Default azureaideploymentregion is canadaeast (

), which doesn't support gpt-4o-mini. https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#assistants-preview

It doesn't make sense to default to a region that won't work.

@pamelafox
Copy link
Collaborator Author

@Jbrocket Ah! Great catch, I'll send a fix for that now.

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.

3 participants