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.

Ahh, I see lol

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?

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.

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!

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…

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!

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.

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.

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.

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.

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.

Removed by mod

What are you talking about? You are the one who ranted about people proving you wrong.

You made a big deal out of someone being perfectly pleasant replying to you.

Your viewpoint of anyone responding to you with anything other than agreement as an attack seems to be the real issue.

I’m not upset, you shouldn’t be either, it’s not that big of a deal.

Removed by mod

Seems like a friendly enough response was given to your comment and you automatically assumed they were only interested in saying you’re wrong.

Having a discussion is not “proving everyone wrong”

I disliked signal app wise, and Matrix app was a buggy mess for me and the 4 other people who tried to use it as well

SimpleX was easy to setup and has been for the most part stable for all of us.

Basically to answer your question, people like different things.

SimpleX isn’t perfect by any means but it seems to be developed at a somewhat decent pace with noticeable improvements being made.

I feel like ChatGPT itself probably has a fairly loose temp setting (just a hunch) and I tend to set my conversations up to be more on the strict side

I imagine that’s why our results differ, it’s strange OpenAI doesn’t let ChatGPT site users or at least premium users adjust anything really yet.

Look at the first question in the my first screenshot. It gets that question correct for “mayonnaise” lol

But it’s able to correct unlike what’s shown in the OP messages.

Extremely semantically it seems but it clearly listens. It’s neat to see how different each person experience is.

Also different tuning parameters etc…could make outputs different. That might explain why mine is seemingly a bit better at listening.