The Future of Multimodal Learning

Weeviate is a search engine that combines image text and sentence embeddings into one. The idea of using multiple models, like for example, clip and sentence embeds in one wave has not been fully explored yet. But I wouldn't be surprised if at some point somebody steps up to say, hey, we can make relations using weeviate as the search engine between two completely different models. And so the more of these types of models we see, I don't know about people we'll come up with, but going from doing something with video or with audio or those kind of things, our users benefits from that again, because they get more capabilities to find potential results.