ssrajadh/sentrysearch

Semantic search over videos using Gemini Embedding 2.

58
/ 100
Established

Splits video into overlapping chunks and embeds them directly using Gemini Embedding 2 or local Qwen3-VL models into a ChromaDB vector database, enabling text queries to match against raw video pixels without transcription. Supports automatic clip trimming, Tesla dashcam telemetry overlay, and offline indexing/search via quantized local models as a free alternative to the API backend.

894 stars. Actively maintained with 101 commits in the last 30 days.

No Package No Dependents
Maintenance 25 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 14 / 25

How are scores calculated?

Stars

894

Forks

45

Language

Python

License

MIT

Last pushed

Mar 28, 2026

Commits (30d)

101

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ssrajadh/sentrysearch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.