Kaizen Development Setup Guide

This guide will walk you through the process of setting up the Kaizen development environment.

Step 1: Clone the Repository

First, clone the Kaizen repository from GitHub:

git clone https://github.com/your-username/kaizen.git
cd kaizen

Step 2: Set Up Environment Variables

Copy the .env.example file to create a new .env file:

cp .env.example .env

Make sure to fill in the necessary environment variables in the .env file.

Step 3: Configure `config.json`

Create a config.json file in the root directory of the project. The general structure should look like this:

{
    "language_model": {
        "provider": "litellm",
        "enable_observability_logging": true,
        "redis_enabled": true,
        "models": [
            {
                "model_name": "default",
                "litellm_params": {
                    "model": "gpt-4o-mini",
                    "input_cost_per_token": 0.000000015,
                    "output_cost_per_token": 0.0000006
                }
            },
            {
                "model_name": "best",
                "litellm_params": {
                    "model": "gpt-4o",
                    "input_cost_per_token": 0.000005,
                    "output_cost_per_token": 0.000015
                }
            },
            {
                "model_name": "CUSTOM_MODEL",
                "litellm_params": {
                    "model": "azure_ai/MODEL_NAME",
                    "api_key": "os.environ/CUSTOM_API_KEY",
                    "api_base": "os.environ/CUSTOM_API_BASE"
                },
                "model_info": {
                    "max_tokens": 4096,
                    "input_cost_per_token": 0.000015,
                    "output_cost_per_token": 0.000015,
                    "max_input_tokens": 128000,
                    "max_output_tokens": 4096,
                    "litellm_provider": "openai",
                    "mode": "chat"
                }
            }
        ]
    },
    "github_app": {
        "check_signature": false,
        "auto_pr_review": true,
        "edit_pr_desc": true,
        "process_on_push": true,
        "auto_unit_test_generation": false
    }
}

Configuration Notes:

model_name is the type of model used for routing. You can have multiple models with the same model_name.
litellm_params.model is the actual model name by provider. Refer to the LiteLLM documentation for more details.
All API keys should be set up in the .env file.
You can set up custom models with custom API keys and base names.

Step 4: Running Examples

Once the setup is complete, you can run any example using the following command:

PYTHONPATH=. poetry run python examples/basic/generate.py

Development and Testing

To test any development changes:

Feel free to update the examples as they use the local Kaizen files.
Create your own tests in the tests directory.

Additional Resources

For more information or if you encounter any issues, please refer to the project's documentation or create an issue on the GitHub repository.

How to Contribute Setting up Various Language models