What can I use for an offline, selfhosted LLM client, pref with images,charts, python code execution

Submitted ⁨⁨9⁩ ⁨months⁩ ago⁩ by ⁨catty@lemmy.world⁩ to ⁨selfhosted@lemmy.world⁩

I was looking back at some old lemmee posts and came across GPT4All. Didn’t get much sleep last night as it’s awesome, even on my old (10yo) laptop with a Compute 5.0 NVidia card.

Still, I’m after more, I’d like to be able to get image creation and view it in the conversation, if it generates python code, to be able to run it (I’m using Debian, and have a default python env set up). Local file analysis also useful.

Is there anything that can tick the boxes? Even if I have to scoot across models for some of the features?

source

Comments

Sort:hotnew top

mitexleo@buddyverse.one ⁨9⁩ ⁨months⁩ ago
You should try cherry-ai.com … It’s the most advanced client out there. I personally use Ollama for running the models and Mistral API for advnaced tasks.

source
- catty@lemmy.world ⁨9⁩ ⁨months⁩ ago
  But its website is Chinese. Also what’s the github?
  
  source
  - happinessattack@lemmy.world ⁨9⁩ ⁨months⁩ ago
    github.com/CherryHQ/cherry-studio
    
    source
- mitexleo@buddyverse.one ⁨9⁩ ⁨months⁩ ago
  It’s fully open source and free (as in beer).
  
  source
mitexleo@buddyverse.one ⁨9⁩ ⁨months⁩ ago
You should try cherry-ai.com … It’s the most advanced client out there. I personally use Ollama for running the models and Mistral API for advnaced tasks.

source
TMP_NKcYUEoM7kXg4qYe@lemmy.world ⁨9⁩ ⁨months⁩ ago
You can tell Open Interpreter to run commands based on you human-language input. If you want local only LLM, you can pair it with Ollama. It works for “interactive” use where you’re asked for confirmation before a command is run.

I set this up in a VM because I wanted a full automatic coding “agent” which can run commands without my intervention and I did not want it to blow up main system. It did not really work though because as far as I know Open Interpreter does not have a way to “pipe” a command’s output back into the LLM so that it could create feedback with linters and stuff.

Another issue was that Starcoder2, which is the only LLM trained on permissive licensed code I could find, only has a 15B “human-like” model. The smaller models only speak code so I don’t know how that would work for agentic usage and the 15B is really slow running on DDR4 CPU. I think agents are cool though so I would like to try Aider which is a supposedly good open source agent and unlike Open Interpreter is not abandonware.

Thanks for coming to my blabering talk, hope this might be useful for someone.

source
hendrik@palaver.p3x.de ⁨9⁩ ⁨months⁩ ago
Maybe LocalAI? It doesn't do python code execution, but pretty much all of the rest.

source
- catty@lemmy.world ⁨9⁩ ⁨months⁩ ago
  This looks interesting - do you have experience of it? How reliable / efficient is it?
  
  source
  - mitexleo@buddyverse.one ⁨9⁩ ⁨months⁩ ago
    LocalAI is pretty good but resource-intensive. I ran it on a vps in the past.
    
    source
  - hendrik@palaver.p3x.de ⁨9⁩ ⁨months⁩ ago
    I think many people use it and it works. But sorry - no, I don't have any first-hand experience. I've tested it for a bit and it looked fine. Has a lot of features and it should be as efficient as any other ggml/llama.cpp based inference solution at least for text. I myself use KoboldCPP for the few things I do with AI and my computer is lacking a GPU so I don't really do a lot of images with software like this. And it's likely going to be less for you than the 15 minutes it takes me to generate an image on my unsuited machine.
    
    source
ViatorOmnium@piefed.social ⁨9⁩ ⁨months⁩ ago
The main limitation is the VRAM, but I doubt any model is going to be particularly fast.

I think phi3:mini on ollama might be an okish fit for python, since it's a small model, but was trained on python codebases.

source
- catty@lemmy.world ⁨9⁩ ⁨months⁩ ago
  I’m getting very-near real-time on my old laptop. Maybe a delay of 1-2s whilst it creates the response
  
  source
catty@lemmy.world ⁨9⁩ ⁨months⁩ ago
I’ve discovered jan.ai which is far faster than GPT4All, and visually a little nicer

source
- voidspace@lemmy.world ⁨9⁩ ⁨months⁩ ago
  Took ages to produce answer, and only worked once on one model, then crashed since then.
  
  source
  - catty@lemmy.world ⁨9⁩ ⁨months⁩ ago
    Try the beta on the github repo
    
    source
- otacon239@lemmy.world ⁨9⁩ ⁨months⁩ ago
  I also started using this recently and it’s very plot and play. Just open and run. It’s the only client so far that feels like I could recommend to non-geeks.
  
  source
  - catty@lemmy.world ⁨9⁩ ⁨months⁩ ago
    I agree. it looks nice, explains the models fairly well. Hides away the model settings nicely, and even recommends some initial models to get started that have low requirements. I like the concept of plugins but haven’t found a way to e.g. run python code it creates yet and display the output in the window
    
    source
breadsmasher@lemmy.world ⁨9⁩ ⁨months⁩ ago
AUTOMATIC1111?

github.com/AUTOMATIC1111/stable-diffusion-webui

source
andrew0@lemmy.dbzer0.com ⁨9⁩ ⁨months⁩ ago
Ollama for API, which you can integrate into Open WebUI. You can also integrate image generation with ComfyUI I believe.

It’s less of a hassle to use Docker for Open WebUI, but ollama works as a regular CLI tool.

source
- catty@lemmy.world ⁨9⁩ ⁨months⁩ ago
  But won’t this be a mish-mash of different docker containers and projects?
  
  source
  - andrew0@lemmy.dbzer0.com ⁨9⁩ ⁨months⁩ ago
    All the ones I mentioned can be installed with pip or uv if I am not mistaken. It would probably be more finicky than containers that you can put behind a reverse proxy, but it is possible if you wish to go that route. Ollama will also run system-wide, so any project will be able to use its API without you having to create a separate environment and download the same model twice in order to use it.
    
    source
- muntedcrocodile@hilariouschaos.com ⁨9⁩ ⁨months⁩ ago
  This is what I do its excellent.
  
  source
- O_R_I_O_N@lemm.ee ⁨9⁩ ⁨months⁩ ago
  ChainLit is a super ez UI too. Ollama works well with Semantic Kernal (for integration with existing code) and langChain (for agent orchestration). I’m working on building MCP interaction with ComfyUI’s API, it’s a pain on the ass.
  
  source
bjoern_tantau@swg-empire.de ⁨9⁩ ⁨months⁩ ago
!localllama@sh.itjust.works

source
just_another_person@lemmy.world ⁨9⁩ ⁨months⁩ ago
Would like fries or a jetpack with that?

source