VoyagerAI multimodal embedding

[HenryUSU]

Voyager AI supports multimodal embedding.
It is not available in the list of used models: https://raw.githubusercontent.com/FlowiseAI/Flowise/main/packages/components/models.json

I tried to add it manually and used a local list, rebuild it and also used the API https://api.voyageai.com/v1/multimodalembeddings in the Credendials settings. But it didn't work unfortunately. Maybe the problem is also in the document loader (e.g. PDF or Word), as I am not sure if they support images of any kind?

So anyway, I think it would be a useful feature.