Skip to main content
Builds a video search application on V-JEPA (Video Joint Embedding Predictive Architecture). Generates vector embeddings for video content and uses vector search to find visually similar clips: a multimodal case where the searchable column is not text.
This example is a runnable notebook in the vectordb-recipes repository rather than a page here.

Open in Colab

Run it end to end in the browser.

View on GitHub

Read the source.