Comment

Comment on Introducing the Nextcloud AI Assistant - local, privacy-respecting, and fully open source 🎉

pixxelkick@lemmy.world ⁨11⁩ ⁨months⁩ ago

Im curious to see what sorts of recommended minimum specs there will be for these features. It is my understanding that these sorts of models require a non negligible amount of horsepower to run in a timely manner.

At the moment I am running Nextcloud on some raspberry pis and, my gut tells me I might need a bit more oomph than that to handle this sort of real time AI prompting >_>;

source

Sort:hotnew top

Dave@lemmy.nz ⁨11⁩ ⁨months⁩ ago
The blog post states:

We build the AI Assistant using a flexible, solution-independent approach which gives you a choice between multiple large language models (LLM) and services. It can be fully hosted within your instance, processing all requests in-house, or powered by an external service.

So it sounds like you pick what works for you. I’d guess on a raspberry pi, on board processing would be both slow and poor quality, but I’ll probably give it a go anyway.

source
- pixxelkick@lemmy.world ⁨11⁩ ⁨months⁩ ago
  Yeah sorry I was specifically referring to the on prem LLM if that wasnt clear, and how much juice running that thing takes.
  
  source
  - Dave@lemmy.nz ⁨11⁩ ⁨months⁩ ago
    Some of the other Nextcloud stuff (like that chat stuff) isn’t suitable on Raspberry Pi, I expect this will be the same. It’s released though, right? Might have to have a play.
    
    source
  - EatYouWell@lemmy.world ⁨11⁩ ⁨months⁩ ago
    You’d be surprised at how little computing power it can take, depending on the LLM.
    
    source
BrownianMotion@lemmy.world ⁨11⁩ ⁨months⁩ ago
the AI that nextcloud is offering uses openAI, sign up get a api key and add it. Your ai requests goto the cloud. (and i couldnt get it to work, constant " too many request" or a straight “failed”)

The other option is the addon " local llm", you download a cutdown llm like llama2 or falcon and it runs locally. I did get thoes all installed, but it didnt work for general prompts.

Nextcloud will probably fix things over time, and the developer who made the local llm plugin will to, but right now this isnt very useful to selfhosters.

source
- TheDarkKnight@lemmy.world ⁨11⁩ ⁨months⁩ ago
  Llama’s getting pretty damn good, check out phind.com if you haven’t yet…its programming better than GPT-4 supposedly!
  
  source
  - BrownianMotion@lemmy.world ⁨11⁩ ⁨months⁩ ago
    I just asked it to write an assembly program for the Intel 8008 uprocessor, and it just knocked it out! That’s not bad for a chip that was released in 1972 !
    
    source
PeachMan@lemmy.world ⁨11⁩ ⁨months⁩ ago
Well, Nextcloud runs like shit on a Pi WITHOUT having to do AI stuff, so…

source
- praise_idleness@sh.itjust.works ⁨11⁩ ⁨months⁩ ago
  People should stop suggesting Nextcloud for Rpi. I really love Nextcloud but it sometimes struggles with even somewhat decent machine.
  
  source
  - neshura@bookwormstory.social ⁨11⁩ ⁨months⁩ ago
    I love Nextcloud but it’s just oh so painfully slow at times
    
    source
    AtmaJnana@lemmy.world ⁨10⁩ ⁨months⁩ ago
    That’s likely a problem with your configuration. Mine was slow too until I set up redis.
    
    source
    -> View More Comments
- redcalcium@lemmy.institute ⁨11⁩ ⁨months⁩ ago
  Nextcloud would struggle on devices with low CPU performance and slow storage speed. A Pi checks all those box. You might increase the performance a bit by running nextcloud from an external SSD but there is no fixing the Pi’s low CPU performance.
  
  source
  - PeachMan@lemmy.world ⁨11⁩ ⁨months⁩ ago
    I’ve tried running NextCloud from a system with a SATA SSD and a Core i7 using WSL…and it still ran like shit.
    
    source
    AtmaJnana@lemmy.world ⁨10⁩ ⁨months⁩ ago
    Not using redis? Mine ran like shit and I almost gave up until I set up file locking and caching.
    
    source
lupec@lemm.ee ⁨11⁩ ⁨months⁩ ago
Yeah, I’m wondering the same and also figure the requirements will be pretty significant. Still, pretty happy things like this and Home Assistant’s recent work on local voice assistants have been popping up.

source