Can you say more about how Polyembed-v1 handles video files? Does it handle the audio or just the video? What do you do about videos longer than a couple of minutes?

It handles both video frames and audio-in-video. So if you wanted, you could search for something that was said in a video and it'll find you the exact segment of it!

We don't use transcription or any post processing. We simply embed the file. Our embedding has an additional inner dimension to support long duration content. So it's [N x D] where D is the embed dimension and N is an internal dimension that varies on the content.