sohamrj

↗ HN profile [ 44.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Last week, I posted SentrySearch, a CLI for semantic video search using Gemini's embedding API. The #1 request was local model support. Turns out Qwen3-VL-Embedding can natively embed video into the same kind of vector…

  2. 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…

  3. I built a semantic search CLI for dashcam footage using Gemini Embedding 2's native video embedding. The interesting part: Gemini Embedding 2 projects raw mp4 video directly into the same vector space as text, no…