Video

What is video RAG?

Video RAG retrieves a moment — a frame, a timestamp, and maybe a transcript line — and gives that evidence to the model.

Updated · Part of What is RAG?

How it works

  • Sample frames, and optionally transcribe the soundtrack.
  • Embed the frames or the transcript windows.
  • The retrieved hit names the clip and the time, then the model answers from that.

What it is not

It is not a vector database of clip titles, and it is not captioning one video inside a chat window.

video RAG: this, and the thing it is confused with

video RAG: this, and the thing it is confused with
ThisNot this
EvidenceA momentA filename
IndexFrames and/or transcript windowsTitles only
Model inputThe hit, not the whole libraryThe entire file on every question

Where Pixeltable fits

Pixeltable builds the frame view and the index on the video table, then a query returns the moment a generator can read.

Questions

How does video RAG work?
Sample frames, and optionally transcribe the soundtrack. Embed the frames or the transcript windows. The retrieved hit names the clip and the time, then the model answers from that.
What is video RAG often confused with?
It is not a vector database of clip titles, and it is not captioning one video inside a chat window.