Quick Start Guide¶

This guide will help you get started with EVOSEAL quickly.

Prerequisites¶

Python 3.10 or higher
Git
pip (Python package manager)

Installation¶

Clone the repository:

git clone https://github.com/SHA888/EVOSEAL.git
cd EVOSEAL

Create and activate a virtual environment:

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

Install the required packages:
```
pip install -r requirements.txt
```

Basic Usage¶

Configure Environment Variables Copy the example environment file and update it with your settings:
```
cp .env.example .env
# Edit .env with your configuration
```
Run the Basic Example

You can run the quickstart example directly:

python -m evoseal.examples.basic.quickstart

Or use it in your code:

from evoseal import EVOSEAL

# Initialize EVOSEAL
evoseal = EVOSEAL()

# Define your task
task = "Create a function that sorts a list of dictionaries by a specific key"

# Run evolution
result = evoseal.evolve(task, max_iterations=10)

# View results
print(f"Best solution: {result.best_solution}")
print(f"Fitness score: {result.fitness}")

Advanced Usage¶

Custom Fitness Function¶

def custom_fitness(solution):
    # Implement your custom fitness logic
    score = 0
    # ... evaluation logic ...
    return score

evoseal = EVOSEAL(fitness_function=custom_fitness)

Using Different Models¶

from evoseal.models import OpenAIModel, AnthropicModel

# Use OpenAI
gpt4 = OpenAIModel(model="gpt-4")

# Or Anthropic
claude = AnthropicModel(model="claude-3-opus")

evoseal = EVOSEAL(model=claude)

Command Line Interface¶

EVOSEAL also provides a CLI for quick tasks:

# Run evolution from command line
evoseal evolve --task "Your task description" --iterations 10

# View help
evoseal --help

Next Steps¶

Explore the User Manual for detailed usage instructions
Check out the API Reference for advanced features
Read the Architecture Overview to understand how EVOSEAL works

Getting Help¶

For questions or issues, please open an issue on GitHub.

Last update: 2025-06-22
Created: 2025-06-17