Viewing profile — sohamrj

Does this work reliably? Don't ChatGPT, Gemini, etc. change up their DOMs frequently and use bot detection to prevent this exact use case?

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 em…

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 em…

ur not wrong

haha no i'm driving the tesla and that clip is from the left repeater camera (teslas record from all around the car)

you're right that the code uses ffmpeg to downsample the chunks to 5fps before sending them, but that's only a local/bandwidth optimization, not what the api actually processes. re…

yea, it's so events on a chunk boundary still get captured in at least one chunk. i haven't had the chance to do formal benchmarks on overlap vs. no-overlap yet. the 5s default is …

dashcam is just one of the use cases and the one i tested on. but this could theoretically work with any kind of video footage like home security footage

Yeah, this is a great idea, I’ve actually been thinking about exactly this as the next logical step. SentrySearch already returns precise in/out timestamps for any natural-language…

I've found I have to be very specific to get the clip I'm searching for. For example, "car cuts me off" just returned a clip of a car driving past my blindspot. But, "car with bike…

Thanks! Yeah that would be pretty cool, but continuous indexing would be pretty expensive now, because the model's in public preview and there are no local alternatives afaik. This…

Totally valid concern. Right now the cost ($2.50/hr) and latency make continuous real-time indexing impractical, but that won't always be the case. This is one of the reasons I'd w…

Not aware of any that do native video-to-vector embedding the way Gemini Embedding 2 does. There are CLIP-based models (like VideoCLIP) that embed frames individually, but they don…

Yes to both. The embedding is over raw video frames, so anything visible (text, signs, captions) gets captured in the vector. And Gemini Embedding 2 extracts the audio track and em…

dashcam and home security footage are the 2 main ones i can think of. a bit expensive right now so it's not as practical at scale. but once the embedding model comes out of public …

as of now, no threshold but that is planned in the future. for example, for now if i search "cybertruck" in my indexed dashcam footage, i don't have any cybertrucks in my footage, …

gemini embedding 2 converts straight video to vectors. in this case, dashcam clips don't have audio to transcribe and even if they did, it would be useless in the 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 "gre…

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 t…