InkChatGPT VS nixos-config

I'm learning LLM at the moment, RAG particularly. [1]

I ended up built InkChatGPT as my learning project and it was huge fun. It is an AI Agent that could help learning from multiple documents and you can chat with it, thank Chat PDF GPT.

I use LangChain as LLM framework to simplify the backend, and using Streamlit as front end UI and deployment. Using OpenAI `gpt-3.5-turbo` model, Use HuggingFace embeddings to generate embeddings for the document chunks with `all-MiniLM-L6-v2` model.

To be honest, coming from Mobile development background, learning about ML and reading about LLM models, prompt tuning and various techniques really opens my mind, but the vast information and knowing how to start is difficult.

[1] InkChatGPT: https://github.com/vinhnx/InkChatGPT

I also took a lot of inspiration from this NixOS config that I think demonstrates a lot of things you can do with them.

Check this repo for reference https://github.com/MatthiasBenaets/nixos-config

The other one I've seen seems more elegant, but I've only seen once and doesn't seem to be fully explain by the author: https://github.com/MatthiasBenaets/nixos-config/blob/master/flake.nix I've tried what he's showcasing here, but it doesn't work the variables are undefined and the tips given by nix-rebuild aren't enough for me to make sense of it.

# nixos-generate-config --root /mnt # git clone https://github.com/matthiasbenaets/nixos-config /mnt/etc/nixos/ (I think this can also be avoided I forgot to check this :| ) # cp /mnt/etc/nixos/hardware-configuration.nix /mnt/etc/nixos/nixos-config/hosts//. # cd /mnt/etc/nixos/ # nixos-install --flake .#