Skip to content
This repository has been archived by the owner on Jun 3, 2024. It is now read-only.

Latest commit

 

History

History
60 lines (44 loc) · 2.16 KB

index.md

File metadata and controls

60 lines (44 loc) · 2.16 KB

📝 This project and its contents were created with the assistance of OpenAI's GPT-3.5 and GPT-4.

PyGPTPrompt

PyGPTPrompt is a CLI tool designed to enhance user interactions with advanced AI models. It specializes in managing context windows, optimizing the long-term memory performance of models like OpenAI's GPT-3.5, GPT-4, and those supported by the llama.cpp Python API. By streamlining data ingestion and facilitating task automation, PyGPTPrompt serves as an effective interface for AI model interaction.

Prerequisites

  • python 3.10 or later

  • pipx

  • poetry

  • Minimum Hardware

    • Quad-Core Processor
    • 8 GB CPU RAM
    • 6 GB GPU VRAM

  • Recommended Hardware

    • Octa-Core Processor
    • 64 GB CPU RAM
    • 24 GB GPU VRAM

Features

  • Context Window Management: PyGPTPrompt's core functionality lies in its efficient management of context windows, enhancing the short-term memory performance of AI models.

  • Data Ingestion: It simplifies the process of feeding data into AI models, enhancing their long-term memory performance.

  • Task Automation: PyGPTPrompt enables effective task automation with AI models, saving time and improving productivity.

  • Multiple Model Support: It integrates with OpenAI and GGML models, supporting those quantized to 4, 5, and 8-bit variations supported by the llama.cpp library.

  • First-Class Support for OpenAI GPT Models: Designed with OpenAI's GPT models in mind, PyGPTPrompt integrates with these AI models through their functions API.

  • Flexible Configuration: Comes with comprehensive configuration files for customization of various parameters and settings, catering to a wide range of use cases and requirements.

Development Status

PyGPTPrompt is currently in an experimental prototype phase. While functional and showing promising potential, it is under active development and not yet production-ready. The solo developer behind this project is committed to refining and enhancing PyGPTPrompt, making it a versatile tool for managing AI models' context windows and facilitating user interactions.