codeproject.ai

[tulip patrol]

(Please accept my apologies if this isn't the right sub-group to paste a general setup question)
Hello immich-gurus, I am looking to understand whether:

1. machine learning algorithm can be a plug-and-play? E.g. rather than using built-in ML for facial recognition, could i employ existing facial recognition algorithm i have running on codeproject.ai server? I employ cpai to process live video streams from various cameras for facial detection. I understand API calls to/from different algorithms will be a heavy lift but was wondering if there's a design intent to move towards such an architecture?
2. I understand that hwaccel docker compose can be run on a machine different to immich container. My VM with immich doesn't have a GPU. cpai VM does have an NVIDIA A100 but no docker environment (and I'd prefer to not install it there). To start with, were I to install docker on VM w/ the GPU, then will immich container be able to refer to it via a simple change in immich docker compose paths?

[stark notch]

:wave: Hey @tulip patrol,

Thanks for reaching out to us. Please follow the recommended actions below; this will help us be more effective in our support effort and leave more time for building Immich .

References

• Container Logs: docker compose logs docs
• Container Status: docker compose ps docs
• Reverse Proxy: https://immich.app/docs/administration/reverse-proxy

Checklist

1. :blue_square: I have verified I'm on the latest release(note that mobile app releases may take some time).
2. :blue_square: I have read applicable release notes.
3. :blue_square: I have reviewed the FAQs for known issues.
4. :blue_square: I have reviewed Github for known issues.
5. :blue_square: I have tried accessing Immich via local ip (without a custom reverse proxy).
6. :blue_square: I have uploaded the relevant logs, docker compose, and .env files using the buttons below or the /upload command.
7. :blue_square: I have tried an incognito window, disabled extensions, cleared mobile app cache, logged out and back in, different browsers, etc. as applicable

(an item can be marked as "complete" by reacting with the appropriate number)

If this ticket can be closed you can use the /close command, and re-open it later if needed.

[deep wharf]

1. No. However if you're up for writing some code it might be pretty straightforward to write a server that pretends to be our ML server but instead just sends requests to that service.
2. yes https://immich.app/docs/guides/remote-machine-learning