OpenAlpha_Evolve

🏁 Getting Started

1. Prerequisites:

   • Python 3.10+
   • pip for package management
   • git for cloning
   • Docker: For sandboxed code evaluation. Ensure Docker Desktop (Windows/Mac) or Docker Engine (Linux) is installed and running. Visit docker.com for installation instructions.

2. Clone the Repository:

   git clone https://github.com/shyamsaktawat/OpenAlpha_Evolve.git
   cd OpenAlpha_Evolve
   

3. Set Up a Virtual Environment (recommended):

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

4. Install Dependencies:

   pip install -r requirements.txt
   

5. Set Up Environment Variables (Crucial for API Keys):

   • This step is essential for the application to function correctly with your API keys. The .env file stores your sensitive credentials and configuration, overriding the default placeholders in config/settings.py.
   • Create your personal environment file by copying the example:

     cp .env_example .env
     

   LLM Configuration

   Google Cloud authentication (e.g., via Application Default Credentials (ADC) or service account keys pointed to by GOOGLE_APPLICATION_CREDENTIALS) is a supported method for using Google's LLMs.

   To set up your environment variables for Google Cloud, you can use one of the following methods. These should be added to your .env file:

   # For Google Cloud (Vertex AI / AI Studio)
   # Option 1: Using Application Default Credentials (ADC)
   # Ensure you have authenticated via gcloud CLI:
   # gcloud auth application-default login
   # Or set the GOOGLE_APPLICATION_CREDENTIALS environment variable:
   # GOOGLE_APPLICATION_CREDENTIALS="/path/to/your/service-account-key.json"
   
   # Option 2: Directly using an API Key for specific Google services (e.g., Gemini API)
   # GEMINI_API_KEY="your_gemini_api_key"
   

   This project uses LiteLLM to interface with various LLM providers. For providers other than Google Cloud (e.g., OpenAI, Anthropic, Cohere), please refer to the LiteLLM documentation for the specific environment variables required. Common examples include:

   # OPENAI_API_KEY="your_openai_api_key"
   # ANTHROPIC_API_KEY="your_anthropic_api_key"
   # COHERE_API_KEY="your_cohere_api_key"
   

   Add the necessary API key variables for your chosen LLM provider(s) to your .env file.

6. Run OpenAlpha_Evolve! Run the example task (Dijkstra's algorithm) with:

   python -m main examples/shortest_path.yaml
   

   Watch the logs in your terminal to see the evolutionary process unfold! Log files are also saved to alpha_evolve.log (by default).

7. Launch the Gradio Web Interface Interact with the system via the web UI. To start the Gradio app:

   python app.py
   

   Gradio will display a local URL (e.g., http://127.0.0.1:7860) and a public share link if enabled. Open this in your browser to define custom tasks and run the evolution process interactively.

📜 License

This project is licensed under the MIT License. See the LICENSE.md file for details.