Problem/Motivation

If existing in the free inference - add image embeddings endpoint.

Proposed resolution

Check if it exists
Add it

Remaining tasks

User interface changes

API changes

Data model changes

Comments

marcus_johansson created an issue.

a.dmitriiev’s picture

a.dmitriiev commented

I checked https://huggingface.co/models?inference_provider=all&other=multimodal-em... and also the same search for image embedding. Unfortunately, there are no models for inference provider.

There are models for feature extraction like google/vit-base-patch16-224 or google/vit-base-patch16-384 . But I am not sure that it is what expected in this issue.