There a lot of methods in IR/RAG that maintain structure as metadata used in a hybrid fusion to augment search. Graph databases is an extreme form but some RAG pipelines pull out and embed the metadata with the chunk together. In the specific case of code, other layered approaches like ColGrep (late interaction) show promise.... the point is most search most of the time will benefit from a combination approach not a silver bullet
I have seen engineering shops where the conversation about fixing some small but simple thing before a deadline gets filed into "better to give the consultants reviewing this some low hanging fruit for the snag list."
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 more clear. thanks for bringing this up.
Before there was OpenClaw (nee ClawdBot) the Beads project was multi-agent harness hotness and the agent-mail was part of its success and still getting some work to fix zookeeper type coordination problems with agent messaging sync/async workloads here is some of the new direction if you run into any of the same issues :
Nice turn key solution I like that it comes with it's own email and you don't need to add anything .... I was a fan of this VPS setup service for a beads agent system up from end to end but you need to BYO everything still it's free as in open source so got to thank Sir Dicklesworthstone for putting it together --
BlitzBrowser is a docker image running browsers. It has multiple features to make it easier to run browsers in production. The cloud version is a managed version of the open source project. Since I'm a solo dev, creating it in my free time, I prefer to focus on the open source version only. The open source version has all the features to be run in the cloud.
To replace the cloud version, you can run Blitzbrowser with Scaleway serverless containers and Cloudflare S3 for free or any other cloud providers offering free tier for docker containers and S3 storage.
reply