sohamrj4d ago

Show HN: Gemini can now natively embed video, so I built sub-second video search

Gemini Embedding 2 can project raw video directly into a 768-dimensional vector space alongside text. No transcription, no frame captioning, no intermediate text. A query like "green car cutting me off" is directly comparable to a 30-second video clip at the vector level.

I used this to build a CLI that indexes hours of footage into ChromaDB, then searches it with natural language and auto-trims the matching clip. Demo video on the GitHub README.
Indexing costs ~$2.50/hr of footage. Still-frame detection skips idle chunks, so security camera / sentry mode footage is much cheaper.

https://github.com/ssrajadh/sentrysearch

GitHub - ssrajadh/sentrysearch: Semantic search over videos using Gemini Embedding 2.

Semantic search over videos using Gemini Embedding 2. - ssrajadh/sentrysearch

GitHub
Show threademsign4d ago
Where is the Exit to this dystopia?
Show threadRobotToaster
In the matrix the exit was pay phones, which perhaps explains why our overlords are removing them
Mar 24 at 5:42pmWeb