Prompt Decorators

🚀 Prompt Decorators Project Documentation

Prompt Decorators is a framework designed to enhance the effectiveness of prompts for AI models. By using standard formats and an extensible mechanism, it enables users to share and reuse prompt enhancement features across different AI platforms.

🚀 Quick Start

Prompt Decorators is a framework for improving the effectiveness of prompts in AI models. It uses standard formats and an extensible mechanism, allowing users to share and reuse prompt enhancement features across different AI platforms.

Core Objectives

• Provide a set of standardized prompt modifiers.
• Implement an extensible framework to apply these modifiers.
• Support multiple languages and various input/output formats.
• Ensure interoperability between different AI services.

✨ Features

• Standard Modifier Set: A predefined set of modifiers, including Reasoning, Tone, Example, etc.
• Extensible Framework: Supports user-defined modifiers.
• Multi-platform Compatibility: Compatible with various AI services such as Claude and ChatGPT.
• Parameter Validation: Automatically checks the validity of modifier parameters.
• Dynamic Loading Mechanism: Allows new modifier definitions to be loaded at runtime.
• Documentation Generation Tool: Automatically generates usage instructions for modifiers.

💻 Usage Examples

Basic Usage

import prompt_decorators as pd

# Load available modifiers
pd.load_decorator_definitions()

# Create a modifier instance
reasoning = pd.create_decorator_instance("Reasoning", depth="comprehensive")

# Apply the modifier to the prompt
prompt = "Explain the concept of prompt engineering."
decorated_prompt = reasoning.apply(prompt)

print(decorated_prompt)

Advanced Usage

from prompt_decorators import DecoratorRegistry, ParameterValidator

# Define a new modifier class
class ExampleDecorator:
    def __init__(self, examples):
        self.examples = examples
        
    def apply(self, prompt):
        return f"Based on the following examples, {prompt}: {self.examples}"

# Register the new modifier
DecoratorRegistry.register("Example", ExampleDecorator)

# Use the new modifier
example_decorator = DecoratorRegistry.get("Example")("This is an example.")
prompt = "How to explain this concept?"
decorated_prompt = example_decorator.apply(prompt)
print(decorated_prompt)

📦 Installation

Basic Installation

pip install prompt-decorators

Optional Dependencies

# For Model Context Protocol (MCP) integration
pip install "prompt-decorators[mcp]"

# For development and testing
pip install "prompt-decorators[dev,test]"

# For documentation
pip install "prompt-decorators[docs]"

# Install all optional dependencies
pip install "prompt-decorators[all]"

📚 Documentation

For detailed technical documentation and usage guides, please refer to the official documentation.

📄 License

This project is licensed under the Apache License 2.0. Please refer to the LICENSE file for specific details.

👏 Contribution Guidelines

All contributions are welcome! Please read CONTRIBUTING.md to learn how to contribute to this project.

🙏 Acknowledgments

We would like to thank the following individuals and organizations for their contributions and support:

• Mostapha Kalami Heris: His article "Prompt Decorators: A Simple Way to Improve AI Responses" inspired us to develop this specification and create this repository.
• Synaptiai: The creator and maintainer of this framework and specification.
• Contributors: All outstanding individuals who have contributed to this project.