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

feat(dotAI): Adding fallback mechanism when it comes to send models to AI Provider (OpenAI) #29516

Closed
wants to merge 1 commit into from

Conversation

victoralfaro-dotcms
Copy link
Contributor

@victoralfaro-dotcms victoralfaro-dotcms commented Aug 9, 2024

Supporting a mechanism to implement a fallback strategy when sending requests to out AI provider (OpenAI) required many changes:

  • Not only that but to leave the code open to manage multiple AI providers
  • The code changes also include a way of decoupling the provider and its connection details from the actual fallback strategy so in the future when we support more providers this won't be an issue
  • Since we need a way to notify the user with messages in the UI, this one needed to be propagated all across the different layers until our AI core fallback strategy
  • Rebased recent AI refactors from master
  • Every AI consuming code needed to be updated to the new way of calling for AI functionality
  • Introduced several specific exception to have a better handling or AI related errors
  • Added many integration and unit tests to cover all the scenarios we might encounter

@victoralfaro-dotcms victoralfaro-dotcms force-pushed the 29284-ai-models-fallback branch 3 times, most recently from a6653c9 to 284a8ba Compare August 16, 2024 15:18
@victoralfaro-dotcms victoralfaro-dotcms force-pushed the 29284-ai-models-fallback branch 5 times, most recently from ef0052a to 23138f0 Compare August 22, 2024 20:03
@victoralfaro-dotcms victoralfaro-dotcms marked this pull request as ready for review August 22, 2024 20:03
Copy link
Contributor

@freddyDOTCMS freddyDOTCMS left a comment

Choose a reason for hiding this comment

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

This PR is too long for a real Code review

@dsilvam
Copy link
Contributor

dsilvam commented Aug 23, 2024

Too long to review. Please split into smaller PRs.

@dsilvam dsilvam closed this Aug 23, 2024
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.

4 participants