[kevintouati]

Interesting angle. Does the search use semantic embeddings so it can surface clips by concept rather than filename/metadata? If it nails the retrieval part, that could be the real differentiator.

[correa_brian]

Yeah, exactly. We capture the semantic meaning of each frame and complement the filename/metadata, so both options work.

[akshaymalik1995]

Do we have any metrics on the time taken to index media files or the latency for performing semantic searches on them?