ai-function-helper 0.2.3

A helper for creating AI-powered functions using OpenAI's API

AI Function Helper

Streamline your AI-powered Python functions with ease!

Key Features • Installation • Quick Start • Documentation • Contributing

---

📚 Table of Contents

• Key Features
• Installation
• Quick Start
• Core Concepts
• Advanced Usage
  • Customizing AI Function Behavior
  • Function Formats
  • Synchronous vs Asynchronous Usage
• Error Handling and Debugging
• Examples
• Contributing
• License

🌟 Key Features

• Seamless OpenAI Integration: Easy setup with various AI models (GPT-3.5, GPT-4, etc.)
• Flexible Function Decorators: Customize AI-powered tasks with ease
• Synchronous and Asynchronous Support: Use AI functions in both sync and async contexts
• Robust Error Handling: Automatic retries and comprehensive error management
• Type Safety: Pydantic models for JSON parsing and validation
• Debugging Capabilities: Detailed logging of API interactions
• Function Calling: Support for OpenAI's function calling feature
• Multiple Return Formats: Flexible output handling (JSON, string, raw response)

🚀 Installation

Install AI Function Helper using pip:

pip install ai-function-helper

🏁 Quick Start

Get up and running with AI Function Helper in just a few lines of code:

from ai_function_helper import AIFunctionHelper

# Initialize AI Function Helper
ai_helper = AIFunctionHelper("your-api-key")

# Create an AI-powered function (synchronous version)
@ai_helper.ai_function(model="gpt-3.5-turbo", max_tokens=200)
def generate_short_story(theme: str):
    """
    Generate a short story based on a given theme.
    """

# Use the function
story = generate_short_story(theme="A day in the life of a time traveler")
print(story)

# Asynchronous version
@ai_helper.ai_function(model="gpt-3.5-turbo", max_tokens=200)
async def generate_short_story_async(theme: str):
    """
    Generate a short story based on a given theme (async version).
    """

# Use the async function
import asyncio

async def main():
    story = await generate_short_story_async(theme="A day in the life of a time traveler")
    print(story)

asyncio.run(main())

🧠 Core Concepts

AI Function Helper is built around several key concepts:

1. AIFunctionHelper Class: The main entry point for creating AI-powered functions.
2. AI Function Decorator: Transforms regular Python functions into AI-powered ones, supporting both sync and async usage.
3. Pydantic Models: Ensures type safety and easy validation of AI-generated responses.
4. Error Handling: Built-in mechanisms for handling API errors and retrying failed calls.
5. Debugging: Comprehensive logging options for troubleshooting and optimization.

🔧 Advanced Usage

Customizing AI Function Behavior

Fine-tune your AI functions with various parameters:

@ai_helper.ai_function(
    model="gpt-4",
    max_tokens=500,
    temperature=0.7,
    top_p=0.9,
    frequency_penalty=0.1,
    presence_penalty=0.1,
    timeout=60,
    max_retries=3,
    show_debug=True,
    debug_level=2
)
def advanced_function(input_data: str) -> ComplexResponseModel:
    """
    An advanced AI-powered function with custom settings.
    """

Function Formats

AI Function Helper supports multiple function formats to suit various use cases:

1. Using ai_result Parameter:

   def func(ai_result: ResponseModel, input: str) -> ResponseModel:
   

2. Direct Pydantic Model Return:

   def func(input: str) -> ResponseModel:
   

3. String Output:

   def func(input: str) -> str:
   

4. Unspecified Return Type:

   def func(input: str):
   

Synchronous vs Asynchronous Usage

AI Function Helper now supports both synchronous and asynchronous usage:

1. Synchronous Usage:

   @ai_helper.ai_function(model="gpt-3.5-turbo")
   def sync_function(input: str) -> str:
       """
       A synchronous AI-powered function.
       """
   
   result = sync_function("Hello, AI!")
   print(result)
   

2. Asynchronous Usage:

   @ai_helper.ai_function(model="gpt-3.5-turbo")
   async def async_function(input: str) -> str:
       """
       An asynchronous AI-powered function.
       """
   
   async def main():
       result = await async_function("Hello, AI!")
       print(result)
   
   asyncio.run(main())
   

The ai_function decorator automatically detects whether the decorated function is synchronous or asynchronous and adapts accordingly.

🐞 Error Handling and Debugging

Enable detailed logging and set retry attempts:

@ai_helper.ai_function(max_retries=3, show_debug=True, debug_level=2)
def debug_example(input_data: str) -> ResponseModel:
    """
    This function will display detailed debug information and retry up to 3 times on failure.
    """

📘 Examples

1. Simple Text Generation (Synchronous)

@ai_helper.ai_function(model="gpt-3.5-turbo", max_tokens=100)
def generate_haiku(theme: str) -> str:
    """
    Generate a haiku based on the given theme.
    """

haiku = generate_haiku(theme="autumn leaves")
print(haiku)

2. Complex Data Processing (Asynchronous)

class RecipeResponse(BaseModel):
    name: str
    ingredients: List[str]
    instructions: List[str]

@ai_helper.ai_function(model="gpt-4", max_tokens=500)
async def generate_recipe(cuisine: str, dietary_restrictions: str) -> RecipeResponse:
    """
    Generate a recipe based on the given cuisine and dietary restrictions.
    """

async def main():
    recipe = await generate_recipe(cuisine="Italian", dietary_restrictions="vegetarian")
    print(f"Recipe: {recipe.name}")
    print("Ingredients:", ", ".join(recipe.ingredients))
    print("Instructions:", "\n".join(f"{i+1}. {step}" for i, step in enumerate(recipe.instructions)))

asyncio.run(main())

🤝 Contributing

We welcome contributions to AI Function Helper! Here's how you can help:

1. Fork the repository
2. Create a new branch (git checkout -b feature/amazing-feature)
3. Make your changes
4. Commit your changes (git commit -m 'Add some amazing feature')
5. Push to the branch (git push origin feature/amazing-feature)
6. Open a Pull Request

Please read CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.

📄 License

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