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.
I’ve used it productively this week by…
This is so exciting! Go little mouse, you can do it
My neighbour’s cat was also a Loki, very chill for a trickster god, and sadly passed away a few weeks ago. Glad yours is enjoying the race. We’re considering getting a cat, might give it the same name, just spelled Lowkey.
Built a booby-trap device to cover porch pirates in glitter. Oh no, such a disgrace.
Ah, the old game of cat and mouse
I guess Australia.gov can be the site in the middle handing out the tokens
Arrogance, then more arrogance.
If you want to save money, start looking at the largest salaries.
Jellyfin is also available as a native DSM package through SynoCommunity, FWIW.
Found the flatpak hater