Skip to content

CrunchysPixelPillow/Project_AHaxe

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AHaxe


Project AHaxe Is a Very Tiny 60+ Line libaray for local ai models using LM Studio

Made to provide a layer of syntax for interacting with your ai models without using something trivial like Javascript or Python

This libaray works by using Array stack like logic where a single multiline string is appended each argument then is saved to file using build statement

Usage


[Setup] *
    AHaxeLibaray.Setfile("Filename.py")
    
    AHaxe.SetModel("Full model name") - 
        * Enter the model you wish to use, must be downloaded.. 
        * you can get fullname from lmstudio app..
        * This was tested using "ibm/granite-3.1-8b"
        
    AHaxe.Build(Void)
        * Put this at the very end of you code..
        * unless you insted to use more then one model such as conditional loops
        
[Statements] *
    AHaxe.Ask("whats 1 + 2", "variable") -
        * [Best used with syntax("print(variable)"]
        
    AHaxe.Syntax('print(answer)')
        * Made to be able to write python and haxe same file, 
        * without changing target compile
        * Recommended for parsing model's answer/output
    
[Helpers] *
    * AHaxe.Info(Void) - Displays Basic Usage

[Output] *
    import lmstudio as lms
    
    model = lms.llm('ibm/granite-3.1-8b')
    question1 = model.respond("whats 1 + 2 just say answer only")
    print(f"Answer[{question1}")
    
[Others] *
    Imports -
        * Import AHaxe.*;
        * Import AHaxeLibaray.*;
        
    Comments -
        * For requirments it depends when parts of std are decaptated
        * Latest installment or close to it will most likely work fine
        
        * PyProject.toml is for poetry,
        * because i dont use poetry often please tell me if something if off/wrong

[Links] *
    Java SDK [Eclipse] - https://adoptium.net/
    Haxe ToolKit [Home Page] - https://haxe.org/
    The Unlicense [Licence] - https://unlicense.org/
    Haxe Libaray [For Color] - https://github.com/dionjwa/hx-color-trace
    LM Studio [Made Around] - https://lmstudio.ai/

Requirments [Pick One]


  • The Haxe Toolkit
  • Java SDK [Not Made Yet]
  • Shortcuts Batch and Zsh[Not Made Yet]
  • Libaray Installers Batch and Zsh[Not made Yet]
  • pip lmstudio module

Credits [Libaraies Used]


About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Packages

No packages published