[Bug] gpt-4o cannot input image

[evilchris]

💻 Operating System

Windows

📦 Environment

Official Preview

🌐 Browser

Chrome

🐛 Bug Description

[Bug] gpt-4o cannot input image

🚦 Expected Behavior

No response

📷 Recurrence Steps

No response

📝 Additional Information

No response

[lobehubbot]

👀 @evilchris

Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible. Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事，并尽快回复您。 请确保您已经提供了尽可能多的背景信息。

[heshunme]

Could you provide more details? This feature seems to be working fine on my end.

[Henry-Suen]

Could you provide more details? This feature seems to be working fine on my end.

I am having the same issue. Because when you change the model to 4o, the upload image button will go gray and not clickable. How do you manage to upload an image?

And here Arvinxx said "The current logic to determine whether multimodality is supported is whether the model name contains vision"

https://github.com/lobehub/lobe-chat/discussions/1025#discussioncomment-8104434

[ChrisXHLeung]

after I upgraded to the latest version, and cleaned my browser's data and history, It worked again. It indicated that there could be some bug in the search and adding an online model which not originally supported.

[Henry-Suen]

Ah, I think they have solved it cuz after refreshing the model list. ( The "Get Model List" button in the Settings>Language Model. Version 0.159.12) The 4o got some icons and context length. Now I can upload images, too.

[softdream1981]

but we still can't upload .doc .pdf ?

[lobehubbot]

👋 @{{ author }}
Since the issue was labeled with 🤔 Need Reproduce, but no response in 3 days. This issue will be closed. If you have any questions, you can comment and reply.
由于该 issue 被标记为需要更多信息，却 3 天未收到回应。现关闭 issue，若有任何问题，可评论回复。

[lobehubbot]

✅ @evilchris

This issue is closed, If you have any questions, you can comment and reply.
此问题已经关闭。如果您有任何问题，可以留言并回复。