use-context-selector VS KoboldAI-Client

Use jotai, or as someone else mentioned, zustand. React Context out of the box requires a very deliberate mental model due to a lack of tooling around selecting slices of state. This is why packages like react-context-selector exist: https://github.com/dai-shi/use-context-selector

Unless I've missed it, context doesn't have selector IIRC. You'd have to use a third party solution useContextSelector

How does this differ from https://github.com/dai-shi/use-context-selector?

you can always split out context state or use a library to help with rerender issues like https://github.com/dai-shi/use-context-selector, or just switch to jotai or something else if you want something more ergonomic or better design patterns.

If you don't want to swap out useContext, you could always use useContextSelector, which helps you limit what props in the context should rerender the component.

I wouldn't call this easy

It wouldn't be clear to anyone learning Context API either. At least, not using official docs. Because Context API is not supposed for state management, and if you for some unknown reasons try to roll your own state management on top of it, you have to use tricky libraries to work around the issues resulting from such abuse.

Any time anything in the context changes, any component that is consuming it will re-render. If you use it for frequently changed values, this library is needed to reduce unnecessary re-renders.

Use of this implementation of useContextSelector

Another technology I use regularly is Redux. But this time I wanted to manage the global state in a simpler and clearer way just using React hooks. I decided to go with a simple useReducer combined with theuseContextSelector hook which will avoid the whole application’s re-render caused by the native useContext hook.

You can use KoboldAI to run a LLM locally. There are hundreds / thousands of models on hugging face. Some uncensored ones are Pygmalion AI (chatbot), Erebus (story writing AI), or Vicuna (general purpose).

GPT-J 6B is a pretty weak and outdated model. Nerys 13B would probably give you better replies but they lean more towards SFW stuff. Erebus was their best model for erotic roleplay but they removed it as it went against Google's TOS. You can check out their documentation here.

If you do have that kind of hardware, the next step would be looking for what model to run. I came across Kobold's models. Their main github page is here: https://github.com/KoboldAI/KoboldAI-Client

Then there are graphical user interfaces like text-generation-webui and gpt4all for general purpose chat. There are also KoboldAI and SillyTavern, they have focus more on storytelling and roleplay and have tools to improve that.

And finally the folks from the KoboldAi do some interesting stuff with Pseudocode and Soft-Prompts that might also be relevant.

Click this link. ---> https://github.com/KoboldAI/KoboldAI-Client/tree/main

Do you believe the problem could be that my KoboldAI is outdated? I did download the one from henk717 at https://github.com/KoboldAI/KoboldAI-Client but it was a little while ago.