support multimodal embedding model(such as WeMM-Embedding) to extend file types

[lalalic]

What problem does this solve?

https://github.com/Tencent/WeMM-Embedding.
WeMM-Embedding is a family of universal multimodal embedding models.

Proposed solution

WeMM-Embedding is a family of universal multimodal embedding models. is it possible to use it for any file type a multimodal embedding model supports?

Example usage