curbstickle_lw

Would you buy a car with a big dick and balls for a logo, but you can pay extra to have it removed?

Have you ever seen corporate branded truck nuts? Because I have, and those companies paid to add it in.

That was not the issue with tesseract or its dev, let’s be honest.

This is… beautifully without any soul or personality. Its so fitting.

I want to remind everyone to keep on topic. Disparaging people for whatever reason is not on topic.

If you see something problematic, please report rather than respond. Your comment in response will be nuked along with the original problem comment.

All set thanks!

@frey@lemmy.world please update with the appropriate tag/disclosure per rules 7/8

Thanks

Its a pretty big stretch to call this self-hosting related…

Locking the thread.

Please add your disclosure. See rule 8. Locking for now + cleanup.

What I might consider is a “winterized” variable per hose/pipe that may be a concern, and only notify if winterized is false for those, and have the notification list specifically not winterized.

That state would be manual per, but then you would be able to get a more meaningful reminder to only those that would be at risk.

No worries!

Please review rule 7 and tag as appropriate. If AI assisted at any level, please also add the required disclosure.

Up until the point the resources available (CPU/ram/storage) become a problem.

That said, managing those apps as installations can be troublesome, which is why people like podman/docker. Updates are more contained, system updates don’t break services, and vice-versa.

A more comprehensive option is to use Proxmox or similar to manage services as a combination of Virtual Machines, LXC’S (Linux containers), and maybe podman/docker on a VM. Note that Proxmox techincally supports importing a docker container as an LXC, but this is a one-time action. Not recommended.

Navidrome and pihole are the easy ones on that list also. Jellyfin itself is easy, but you aren’t going to be transcoding video on the fly, so make sure its in a format that is friendly to all of your devices, transcoding in advance if needed.

I’d sum it up with:

“Ew.”

Its one thing to offer bespoke customization for businesses. Its entirely another to work to prevent any indication that the software is being run by someone other than the creator of the software. IMO, it goes against self hosting as a practice.

It could be everything I want and more, and it would immediately turn me away. Which, in turn, would also turn me away from recommending it to others, including businesses.

I’d call it a pretty bad strategy.

This post is off-topic for the community.

That said, its a topic people here are quite passionate about, which is why it gathered quite a bit of comments already.

I’m going to leave it up, but locked.

Secure enough I suppose.

f2b at the FW, auth with MFA for anything exposed, anything local only has restricted access at the FW level, with exposed (via proxy) and local-only (separate proxy) on different vlans. Each service is (typically, with some exceptions) an LXC, with additional rules and templated out based on use case. The few cases where docker is involved is local-only and that has its own vlan with additional rules.

rclone crypt

Appreciate that you have the disclosure, but your account is too new to post promo. Your account will need to be at least 30 days old.

Please post again once you’ve met the requirements! In the meantime, please stick around and get to know the other folks here as well.

This post is tagged properly and has a full disclosure.

Off topic comments will be removed.

You can, but you need their app.

That isn’t something I’m going to do, so I tag manually instead.

Well, perfect use case for the test immich instance!

I’ve got a few day trips recently that will make for good tests for over the weekend.

The immich service connection.with writeback is awesome!

My kids have some dinky little digital cameras with no GPS or WiFi or anything, just writes photos locally to microsd, so obviously no location data. I use my phone, sure, but when traveling I’ll use my DSLR that also has no GPS (OK it does have WiFi, but I don’t use it).

Which turns into me tagging every time we get back from somewhere.

Going to give that immich link a try!

Its relatively new (past 6 weeks or so?) due to an influx of projects and a lot of repeat questions, and after some community discussions its where things landed.

Please update with the tag per rules 7 & 8 and add a disclosure if needed

Thanks!

No worries, just clarifying, which I’ll need to add into the rules as well somehow…

even if you are promoting someone else’s project/app.

To correct you on this - ifyou are linking someone else’s project/app, it would be entirely impossible to require a disclosure. A tag is a nice-to-have depending on how visible those elements are, but the paid/30 day account age for f/loss would still apply.

I suspect I’ll need to clean up the language some if this is the takeaway.

Aside from “local model”, you might see things like whisper.cpp, llama.cpp, ollama, or “OpenAI compatible endpoint”, or a reference to getting models from HuggingFace (you can think of it like github for llm’s - its more and less, but accurate enough for what we’re talking about here).

whisper.cpp is a c++ implementation of whisper (ASR as mentioned), llama.cpp is a high performance and lightweight tool to support llm/llm inference, ollama is a very user friendly way to do the same, and OpenAI compatible endpoint is just using the protocol for communication, so you can point the client at llama.cpp or similar running on the same machine or another you have access to.

Most things with an extemely tight purpose like this (like listening for some birds singing) will use much leaner models, and may be able to run even from a phone.

Audio processing by ai can absolutely happen on a pi.

As an example, whisper.cpp is a high performance speech recognition model, and it does a great job. The biggest version of it as a model requires less than 5GB to live fully in memory, the large model at about 1.5billion parameters, and it works great even CPU only.

The one used most often is small, which has about 244million parameters, and needs about a gig of ram and nothing more.

For a pi 5, usually the base or tiny model are used. Small could be used in most scenarios, but tiny and base are able to run real-time.

So it depends for how local - sometimes its all self contained and can do just fine on a pi, sometimes its local in that it needs an LLM endpoint to hit, but that can be running on another system entirely.

It would really depend on the project for how/where/why for a definition of local.

A quick general awareness comment:

A post about a project not by the original creator is not a promo post. A user will not necessarily know the details to provide a disclosure unless a project explicitly has on in their repo.

Requiring it on a project post like this (“Here’s a cool thing I found!”) is not doable.

Thanks, please update the title with [AIP] as well, so people can filter.

Choosy self-hosters choose Debian.

That said, I don’t recommend hosting software at the bare metal level - use VMs or containers. Far easier to manage and isolate.