Skip to content
Tech News
← Back to articles

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

read original get Video Search API Tool → more articles
Why This Matters

The integration of Gemini's native video embedding with a semantic search system like SentrySearch marks a significant advancement in dashcam footage analysis. This technology enables rapid, precise retrieval of relevant video clips through natural language queries, streamlining workflows for security, law enforcement, and consumers alike.

Key Takeaways

SentrySearch

Semantic search over dashcam footage. Type what you're looking for, get a trimmed clip back.

ClawHub Skill

demo.mp4

How it works

SentrySearch splits your dashcam videos into overlapping chunks, embeds each chunk directly as video using Google's Gemini Embedding model, and stores the vectors in a local ChromaDB database. When you search, your text query is embedded into the same vector space and matched against the stored video embeddings. The top match is automatically trimmed from the original file and saved as a clip.

Getting Started

Clone and install:

git clone https://github.com/ssrajadh/sentrysearch.git cd sentrysearch python -m venv venv && source venv/bin/activate pip install -e .

Set up your API key:

... continue reading