ChatALL VS BrainChulo

First of all, I'd like it to be distributed for users to install as a hub running independently from any browser in the background - although with the possibility of accessing it's interface through a browser if necessary. If I'd have to give you some working examples of similar solutions, it would be something like connection of such apps like ChatAll with a service called SAMP that interconnects multiple apps/services provided by ESA CDPP and related to space weather and multiple satellite missions (http://3dview.cdpp.eu) - yup, that's yet another of those weird hobbies of mine :P

Source: ChatALL/wiki

For some reason, software developers and AI experts seem to be focused on achieving multimodality by extending capabilities of individual models and training them on different sets of data - while my plan is to make them work together. Maybe I should try contacting someone responsible for the 'HuggingFace LLM Arena' and propose to add a function that would allow the competing models to speak to each other - I think that it's a quite good way of evaluating model's 'strength'. There are multiple apps and sites that allow user to speak with multiple models simultaneously - ChatAll is a nice example - and I think that allowing all those models to speak with each other is the most obvious function that should be added to such apps...

--> https://github.com/sunner/ChatALL

On BrainChulo, we’re going 100% guidance mode, see for instance an implementation of Chain of Thoughts on top of a thin guidance wrapper: https://github.com/ChuloAI/BrainChulo/blob/main/app/guidance_tooling/guidance_agent/agent.py

Awesome resource! If I may suggest that you'd add one, some friends and I are working on data retrieval with llm project as well, with our differentiating marker being that we are trying to implement guidance in order to improve the agent efficiency. If you guys wanna take a look :) https://github.com/ChuloAI/BrainChulo

Plug: https://github.com/iGavroche/BrainChulo - BrainChulo currently works on top of Ooba but uses its own UI interface. Its first goal is to provide a production-level way to do Retrieveal Augmentation on Open Source LLMs via vector stores and good prompt engineering.

Regarding this, I've joined a project that is doing some nice progress on this front. Still WIP but we're getting there, checkout BrainChulo :)

This is exactly what BrainChulo aims to do. You should check it out: https://github.com/CryptoRUSHGav/BrainChulo/ and feel free to drop on the discord to give us your feedback, your use-case, or if you need help getting started.

The download script is broken. I posted a working version on my repo: https://github.com/CryptoRUSHGav/BrainChulo

I'm hoping that many of you brilliant people can join me in our common quest to add long-term memory to our favorite camelid, Vicuna. The repository is called BrainChulo, and it's just waiting for your contributions.