bug: The "Image" - Upload Button is always grayed out

[EkkehardDomning]

Jan version

Jan v0.5.15 (same on lates nightly build)

Describe the Bug

The "Image" menu item in the popup menu that open by clicking on the paper clip icon in the text enter field is always grayed out and is not accessible.

Hello,
I am very new using this very nice tool and may just ask something trivial.
I was able to activate the usage of local files for analyzing by activating "Experimental mode" and "Retrieval". Now I can "upload" PDF documents to allow questions on it.
Now I expected that this would work with images too, but the menu item is always disabled.
The Help page says:
"Once enabled, you should be able to upload file(s) & image(s) from threads input field
Ensure that you are using a multimodal model.
File Search: Jan currently supports PDF format
Vision: only works with local models or OpenAI models for now"

I am a bit unsure about the term "multimodal model", but I found that the "LLaVA" Model is such a model and should support image processing. I downloaded and selected this model. This should cover the term " only works with local models" too. But using this model did not change anything on the described behaviour.

So finally I am clueless and think that this might be a bug.

I am using the Engine Version v0.1.49 and "windows-amd64-avx2".

Thank You very much for reading and hopefully helping.
Ekkehard

Steps to Reproduce

No response

Screenshots / Logs

No response

What is your OS?

• MacOS
• Windows
• Linux