fix(gpt-4o-audio-preview): Remove the vision feature

[laipz8200]

Summary

This LLM is not support vision now.

Screenshots

Before:	After:
...	...

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

[fdb02983rhy]

Hi there, please consider reverting this fix before there is an option for other file types. There are not way to send request to the model with audio file after this fix. Or you can simply rename the "Vision" to "File" Since we have #10679 and #10966. Not sure if it's a good option tho.

Before

After

[laipz8200]

Hi @fdb02983rhy! Please check #10679, you can use file variables in prompt editor directly now.

[fdb02983rhy]

Hi @fdb02983rhy! Please check #10679, you can use file variables in prompt editor directly now.

It works!! Thank you so much:)