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

fix: fix azure open-4o-08-06 when enable json schema cant process content = "" #11204

Merged

Conversation

liujiamingtiny
Copy link
Contributor

Summary

The bug caused by Azure model changes first occurred on November 18, 2024. When using the Azure OpenAI GPT-4o-08-06 model with JSON schema format output, if a tool is invoked and the assistant message content is an empty string, the model fails to respond properly, ultimately resulting in a 500 error. To ensure compatibility, it is necessary to detect when the assistant message involves a tool invocation and replace an empty message content with None to enable proper responses.

Screenshots

debug wiht azure py code

before:
image
image

after:
image
image

debug with dify backend code:

before:

image

after:

image

Checklist

Important

Please review the checklist below before submitting your pull request.

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

@dosubot dosubot bot added size:XS This PR changes 0-9 lines, ignoring generated files. 🐞 bug Something isn't working labels Nov 29, 2024
@crazywoola crazywoola requested a review from laipz8200 November 29, 2024 06:29
@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Nov 29, 2024
@crazywoola crazywoola merged commit 6f9ce6a into langgenius:main Nov 29, 2024
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
🐞 bug Something isn't working lgtm This PR has been approved by a maintainer size:XS This PR changes 0-9 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants