dmps 0.1.0

Dual-Mode Prompt System for AI prompt optimization using 4-D methodology

DMPS - Dual-Mode Prompt System

A Python package for AI prompt optimization using the 4-D methodology (Deconstruct, Develop, Design, Deliver).

Features

• Intent Detection: Automatically classifies prompt intent (creative, technical, educational, complex)
• Gap Analysis: Identifies missing information in prompts
• 4-D Optimization: Applies systematic optimization techniques
• Dual Output Modes: Conversational and structured JSON formats
• Platform Support: Optimized for Claude, ChatGPT, and other AI platforms

Installation

From PyPI (Recommended)

pip install dmps

From Source

# Clone the repository
git clone https://github.com/MrBinnacle/dmps.git
cd dmps

# Install in development mode
pip install -e .

Prerequisites

• Python 3.8+
• pip (Python package manager)

Development Installation

1. Clone the repository:

   git clone https://github.com/MrBinnacle/dmps.git
   cd dmps
   

2. Create and activate a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows: .\venv\Scripts\activate
   

3. Install the package in development mode:

   pip install -e .
   

Usage

Quick Start

from dmps import optimize_prompt

# Simple optimization
result = optimize_prompt("Write a story about AI")
print(result)

Advanced Usage

from dmps import PromptOptimizer

optimizer = PromptOptimizer()
result, validation = optimizer.optimize(
    "Explain machine learning",
    mode="conversational",
    platform="claude"
)

print(result.optimized_prompt)

CLI Usage

# After pip install dmps
dmps "Your prompt here" --mode conversational --platform claude

# Or using module syntax
python -m dmps "Your prompt here" --mode conversational --platform claude

# Interactive mode
dmps --interactive

# Help
dmps --help

Development

Running Tests

python -m pytest tests/

Code Quality

# Type checking
pyright src/

# Linting
flake8 src/

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.