Coder Social home page Coder Social logo

karajan421 / auto-gpt-powershell Goto Github PK

View Code? Open in Web Editor NEW

This project forked from thecompace/auto-gpt-powershell

0.0 0.0 0.0 117 KB

AutoGPT is a compact, modular, and user-friendly PowerShell interface for text generation with GPT-4 language models or OpenAI's API. It supports offline usage with GPT4All and offers customizable plugins for input, output, and startup configurations. Users can seamlessly switch between local GPT-4 models and OpenAI API.

License: MIT License

PowerShell 100.00%

auto-gpt-powershell's Introduction

AutoGPT_PS

AutoGPT_PS is a PowerShell script that runs GPT-4, processes user input, and returns generated responses. The script includes a plugin system that allows for easy customization of input processing, output formatting, and more.

Usage

  1. Download the AutoGPT_PS repository.
  2. Place the GPT-4 model file (in .bin format) in the same directory as the AutoGPT.ps1 script.
  3. Run the AutoGPT.ps1 script.

Options

  1. Change Model: Allows selection of a .bin file to use for GPT4All. Example: gpt4all-lora-quantized.bin.
  2. Toggle Pause: Enables or disables pausing after every iteration of the main loop. Default value: y (pause).
  3. Change Seed: Sets the seed value for GPT4All. Default value: `` (use the first generated seed) ('0' will use a random seed everytime.).
  4. Change Loop Count: Sets the number of loops for the main loop. Default value: 10 (ten loops).
  5. Toggle Use ChatGPT: Enables or disables the use of the OpenAI Chat API. Default value: False (disabled).
  6. Set OpenAI Key: Sets the OpenAI API key.
  7. OpenAI Models: Allows selection of an OpenAI model from the available options: text-davinci-003, gpt-3.5-turbo, and gpt-4. Default value: text-davinci-003.
  8. Turn On Debug: Enables or disables debug messages at most steps of the scripts. Default value: False (disabled).

To update these options, select "y" when it prmpts "Do you want to check options? (y)es/(n)o:" at the start.

Examples

In the "examples" folder there are the examples for a run using each model. GPT4ALL is almost useless, but a better plugin that formats for GPT4All might help, but I think it is the model, feel free to add your own implementations of other GPTs.

Creating Plugins

AutoGPT_PS includes a plugin system that allows for easy customization of input processing, output formatting, and more. There are three types of plugins:

  1. Start plugins
  2. Input plugins
  3. Output plugins
  4. System plugins

Each plugin should be a PowerShell script with a specific naming convention: N_Name_PluginType_Format.ps1, where N is an integer, Name is a descriptive name for the plugin, and PluginType is one of the three types: Start, Input, Output, or System.

To create a new plugin, simply create a new PowerShell script with the appropriate naming convention and place it in the "plugins" folder. The AutoGPT_PS script will automatically discover and run the plugins in the specified order.

Base setup of each plugin type, see the scripts provided in the "plugins" folder.

The plugin system is based on separate modules for different types of plugins:

  1. RunStartPlugins.ps1: Searches for and runs start plugins in the "plugins" folder. Example:

    • plugins/1_Sample_Start_Format.ps1: A sample start plugin that leaves the start message unchanged
  2. RunInputPlugins.ps1: Searches for and runs input plugins in the "plugins" folder. Example:

    • plugins/1_Sample_Input_Format.ps1: A sample input plugin that leaves the prompt unchanged
  3. RunSystemPlugins.ps1: Searches for and runs system plugins in the "plugins" folder. Example:

    • plugins/1_Sample_System_Format.ps1: A sample system plugin that leaves the system message unchanged
  4. RunOutputPlugins.ps1: Searches for and runs output plugins in the "plugins" folder. Example:

    • plugins/1_SessionLog_Output_Format.ps1: A sample output plugin that logs the output to a session file

auto-gpt-powershell's People

Contributors

thecompace avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.