Fingerthief

joined 1 year ago
MODERATOR OF
[–] Fingerthief@infosec.pub 3 points 4 months ago (1 children)

That seems like a pretty naive and biased approach to software to me honestly.

Ease of use, community support, feature set, CI/CD etc..all should come into play when deciding what to use.

Freedom at all costs is great until you limit the community development and potential user base by 90% by using a completely open repo service that 5% of the population uses or some small discord alternative.

So then the option is to host on multiple platforms/communities and the management and time investment goes up keeping them in sync and active.

As with most things in life, it's best to look at things with nuance rather than a hard stance imo.

I may stand it up on another service at some point, but also anyone else is totally free to do that as well. There are no restrictions.

[–] Fingerthief@infosec.pub 3 points 4 months ago

Ahh, I see lol

[–] Fingerthief@infosec.pub 4 points 4 months ago* (last edited 4 months ago) (8 children)

I'm not sure I understand at all?

It's fully open source, can run/connect any number of fully local models as well as the big name models if a user chooses to use them.

Can you expand on what you mean?

[–] Fingerthief@infosec.pub 2 points 4 months ago

Thanks!

Unfortunately currently there isn't a true RAG implementation largely due to the fact that this site/app is fully self contained with no additional servers or database etc..which is typically required for RAG.

For now file uploads are stored in the browser's own local database and the content can be extracted and added to the current conversation context easily.

I definitely want to add a more full RAG system but it's a process to say the least, and if I implement it I want it to be quite effective. My experience with RAG generally has left me quite unimpressed with a few quite decent implementations being the exception.

[–] Fingerthief@infosec.pub 4 points 4 months ago

Web search is definitely something I want to add, haven't quite figured out the route I want to take implementing it just yet though.

Hopefully I can get it added sooner rather than later!

 

cross-posted from: https://infosec.pub/post/13676291

I've been building MinimalChat for a while now, and based on the feedback I've received, it's in a pretty decent place for general use. I figured I'd share it here for anyone who might be interested!

Quick Features Overview:

  • Mobile PWA Support: Install the site like a normal app on any device.
  • Any OpenAI formatted API support: Works with LM Studio, OpenRouter, etc.
  • Local Storage: All data is stored locally in the browser with minimal setup. Just enter a port and go in Docker.
  • Experimental Conversational Mode (GPT Models for now)
  • Basic File Upload and Storage Support: Files are stored locally in the browser.
  • Vision Support with Maintained Context
  • Regen/Edit Previous User Messages
  • Swap Models Anytime: Maintain conversational context while switching models.
  • Set/Save System Prompts: Set the system prompt. Prompts will also be saved to a list so they can be switched between easily.

The idea is to make it essentially foolproof to deploy or set up while being generally full-featured and aesthetically pleasing. No additional databases or servers are needed, everything is contained and managed inside the web app itself locally.

It's another chat client in a sea of clients but it is unique in its own ways in my opinion. Enjoy! Feedback is always appreciated!

Self Hosting Wiki Section https://github.com/fingerthief/minimal-chat/wiki/Self-Hosting-With-Docker

I thought sharing here might be a good idea as well, some might find it useful!

I've added some updates since even the initial post which gave a huge improvement to message rendering speed as well as added a plethora of new models to choose from and load/run fully locally in your browser (Edge and Chrome) with WebGPU and WebLLM

[–] Fingerthief@infosec.pub 3 points 4 months ago (1 children)

This project is entirely web based using Vue 3, it doesn't use langchain and I haven't looked into it before honestly but I do see they offer a JS library I could utilize. I'll definitely be looking into that!

As a result there is no LLM function calling currently and apps like LM Studio don't support function calling when hosting models locally from what I remember. It's definitely on my list to add the ability to retrieve outside data like searching the web and generating a response with the results etc..

[–] Fingerthief@infosec.pub 3 points 4 months ago* (last edited 4 months ago)

Yep that's a pretty good comparison!

I'm curious on what you mean by sourcing training data in an ethical way? I know OpenAI has come under well deserved scrutiny for apparently using content that is hidden behind paywalls without purchasing it themselves in their training data. Which is quite unethical, but aside from that instance I'm interested in hearing some other concerns for my own education.

In general there are definitely loads of models on places like Hugging Face that are fully open source and provide training data sources for many.

I believe for Microsoft's new Phi 3 models they actually generated synthetic data themselves for training as well which is an interesting approach that seems to yield good results.

In the open source LLM world the new Meta Llama 3 models are the latest and greatest, I haven't seen any cause for concerns with it yet. Might be worth looking into those!

[–] Fingerthief@infosec.pub 10 points 4 months ago

I haven't personally tried it yet with Ollama but it should work since it looks like Ollama has the ability to use OpenAI Response Formatted API https://github.com/ollama/ollama/blob/main/docs/openai.md

I might give it go here in a bit to test and confirm.

[–] Fingerthief@infosec.pub 14 points 4 months ago* (last edited 4 months ago) (1 children)

Local models are indeed already supported! In fact any API (local or otherwise) that uses the OpenAI response format (which is the standard) will work.

So you can use something like LM Studio to host a model locally and connect to it via the local API it spins up.

If you want to get crazy...fully local browser models are also supported in Chrome and Edge currently. It will download the selected model fully and load it into the WebGPU of your browser and let you chat. It's more experimental and takes actual hardware power since you're fully hosting a model in your browser itself. As seen below.

[–] Fingerthief@infosec.pub 11 points 4 months ago* (last edited 4 months ago) (2 children)

This app is more of an interface to use while connecting to any number of LLM Models that have an API available. The application itself has no model.

For example you can choose to use GPT-4 Omni by providing an API key from OpenAI.

But you can also connect to services like OpenRouter with an API key and select between 20+ different models that they provide access to as seen below

It also supports connecting to fully local models via programs like LM Studio which downloads models from Hugging Face to your machine and will spin up a local API to connect and chat with the model.

 

I've been building MinimalChat for a while now, and based on the feedback I've received, it's in a pretty decent place for general use. I figured I'd share it here for anyone who might be interested!

Quick Features Overview:

  • Mobile PWA Support: Install the site like a normal app on any device.
  • Any OpenAI formatted API support: Works with LM Studio, OpenRouter, etc.
  • Local Storage: All data is stored locally in the browser with minimal setup. Just enter a port and go in Docker.
  • Experimental Conversational Mode (GPT Models for now)
  • Basic File Upload and Storage Support: Files are stored locally in the browser.
  • Vision Support with Maintained Context
  • Regen/Edit Previous User Messages
  • Swap Models Anytime: Maintain conversational context while switching models.
  • Set/Save System Prompts: Set the system prompt. Prompts will also be saved to a list so they can be switched between easily.

The idea is to make it essentially foolproof to deploy or set up while being generally full-featured and aesthetically pleasing. No additional databases or servers are needed, everything is contained and managed inside the web app itself locally.

It's another chat client in a sea of clients but it is unique in its own ways in my opinion. Enjoy! Feedback is always appreciated!

Self Hosting Wiki Section https://github.com/fingerthief/minimal-chat/wiki/Self-Hosting-With-Docker

[–] Fingerthief@infosec.pub 2 points 1 year ago (2 children)

Interesting, thanks for the info!

I wasn't aware of the update process being used as an attack vector (if it's still a thing) gonna have to read up more on that.

[–] Fingerthief@infosec.pub 5 points 1 year ago (4 children)

I used Apple for the last few years until recently and I can't say I've ever really noticed stuff like apps faking being another app. That's not to say it doesn't happen of course.

I do know the Apple app approval process is definitely more strict than what is required for the Play Store.

I'm not very experienced with Apple or Android development so I'd be curious to hear from devs that use both platforms as well.

1
submitted 1 year ago* (last edited 1 year ago) by Fingerthief@infosec.pub to c/minimalgpt@infosec.pub
 

Changes from release notes

  • Adjusted chat message bubbles max width to take up nearly the entire width of the chat.

  • Increase sized of message label logos and font.

  • Adjusted message font size and line-height for a better reading experience

  • Added a border to one side of message bubbles for some UI design changes

1
submitted 1 year ago* (last edited 1 year ago) by Fingerthief@infosec.pub to c/minimalgpt@infosec.pub
 

I've created a fairly thorough overview of MinimalGPT with all the basic info to get started. Please feel free to take a look!

1
submitted 1 year ago* (last edited 1 year ago) by Fingerthief@infosec.pub to c/minimalgpt@infosec.pub
 

Link to a live version of MinimalGPT that I host, you can always spin up a local version youself via the GItHub project.

201
submitted 1 year ago* (last edited 1 year ago) by Fingerthief@infosec.pub to c/cat@lemmy.world
 
view more: next ›