how is image input used for multi-modal models? #6596
weipienlee
started this conversation in
General
Replies: 1 comment
-
I narrowed it down a bit. It seems that if at least 1 other model supports it that makes the non-supporting one seem to support input image. i.e. if only the non-supported model is listed e.g. "o3-mini-2025-01-31" than it indeed fails to accept an image as input.
error message when only "o3-mini-2025-01-31" is listed:
so that makes sense now |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Using o3-mini model to describe an image surprisingly works at the LibreChat's Azure endpoint while the model officially doesn't support it yet. Test with langchain confirms the lack of support (see code and message below). What actually happens in LibreChat with the input image?
error message:
'Invalid content type. image_url is only supported by certain models.'
update: i'm on 0.7.7
Beta Was this translation helpful? Give feedback.
All reactions