If you do set up a RAG store, please post the tech stack you use as I’m in a similar situation. The inbuilt document store management in ollama+openwebui is a bit clunky.
If you do set up a RAG store, please post the tech stack you use as I’m in a similar situation. The inbuilt document store management in ollama+openwebui is a bit clunky.
I’d be interested to see how it goes. I’ve deployed Ollama plus Open WebUI on a few hosts and small models like Llama3.2 run adequately (at least as fast as I can read) on even an old i5-8500T with no GPU. Oracle Cloud free tier might work OK.
Running an LLM can certainly be an on-demand service. Apart from training, which I don’t think we are discussing, GPU compute is only used while responding to prompts.
Love these posts. Plus every month you get to see the flatpak haters try to convince us we are using the wrong technology.
This is so exciting! Go little mouse, you can do it
Built a booby-trap device to cover porch pirates in glitter. Oh no, such a disgrace.
I guess Australia.gov can be the site in the middle handing out the tokens
And slack capacity can be used effectively e.g., spend some time on process improvement. There’s always some saw to sharpen or some technical debt to repay.
If you want to save money, start looking at the largest salaries.
In fact, asking is frowned upon.
You’re usually safe with Apple’s Type-C port supporting a lot.
Who’s got two thumbs and room for them only?
I don’t see the problem. Type-C ports can replace all those ports. If you want more ports, buy a dock.
This seems a big waste of energy if that 140Wh (504,000 joules) number is correct. That amount of energy is about 2,000 times what it would take to do a very similar thing on a home PC.
Writing a 100 word email with a 7B model would take my PC about 5 seconds, times an increased power use of 50 watts, so 250 joules.
I get that they might be using a much larger model, but the e-mail is not going to be 2,000 times better.
“Accidentally”
Cupboard + DiskStation + OptiPlex = Win
Fedora Silverblue. It does what I need so I can get on with my life.
Tailscale is available as an official DSM package, so if it’s only you accessing it you could still block it from the Internet.
Jellyfin is also available as a native DSM package through SynoCommunity, FWIW.
Found the flatpak hater