very cool, anybody have apparent use cases for this?
Trail and game cams come to mind. "Create a montage of all deer encounters," "Find first appearance of black bear this year," that sort of thing.
Show HN: Gemini can now natively embed video, so I built sub-second video search
81–90 of 118 posts
Re: Show HN: Gemini can now natively embed video, so I built sub-second video search
#82Very impressive! A webhook could be configured to trigger an alarm if a semantic match to any category of activities is detected, and then you basically have a virtual security guard and private investigator. Well played.
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 very well might be a reality in a couple years though!
Could https://qwen.ai/blog?id=qwen3-vl-embedding be a possible local alternative?
Re: Show HN: Gemini can now natively embed video, so I built sub-second video search
#83Does anyone know of an open weights models that can embed video? Would love to experiment locally with this.
A quick search brought up https://qwen.ai/blog?id=qwen3-vl-embedding but I have no idea if it does what Gemini is doing here.
Re: Show HN: Gemini can now natively embed video, so I built sub-second video search
#84Earlier quoted context omitted.
From what I see the code downsamples video to 5 fps, so 1 hour of video is 3600 seconds * 5 fps = 18,000 frames. 18,000 frames * $0.00079/frame = $14.22. A couple dollars more with the overlap. (The code also tries to skip "still" frames, but if your video is dynamic you're looking at the cost above.)
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. regardless of the file's frame rate, the gemini api natively extracts and tokenizes exactly 1 fps. the 5 fps downscaling just keeps the payload sizes small so the api requests are fast and don't timeout. i'll update the readme to make this mo…
Thanks for the details and correction.
Re: Show HN: Gemini can now natively embed video, so I built sub-second video search
#85This seems like something that would be very expensive to run. Do you have some representative figures at a particular resolution and frame rate?
Re: Show HN: Gemini can now natively embed video, so I built sub-second video search
#86Very interesting (not for a dashcam, but for home monitoring).
Most home monitoring only records when there is movement though? So that already compresses the search space a lot. And just zipping forward and back it's pretty easy to quickly find the 30 seconds where there is a figure wallking up to your front door.
Re: Show HN: Gemini can now natively embed video, so I built sub-second video search
#87this can be done locally https://github.com/intel/openvino-ai-video-retrieval-analysi...
Re: Show HN: Gemini can now natively embed video, so I built sub-second video search
#88Multimodal AI will lead to an interesting arms race in ad detection vs ad insertion. I played around with AI ad removal with older Gemini models, but it seems like this would be even more powerful to instantly identify ads (and potentially mute or strip them out). https://notes.npilk.com/experiments-with-ai-adblock
Nice article. I saw someone depicting the future of web search with AI. The conclusion was not the bright future. Simply put, ads will never go away. Either AI providers will get paid for whitelisting ads, or even worse these AI will directly promote advertised products.
Re: Show HN: Gemini can now natively embed video, so I built sub-second video search
#89[dead]