Installation

Prerequisites

The weco CLI currently supports Python version 3.8 and above.

Install the weco CLI using pip:

pip install weco

Install from source:

git clone https://github.com/wecoai/weco-cli.git
cd weco-cli
pip install -e .

Tip: We recommend using a virtual environment.

Weco requires API keys for the LLMs it uses internally. Choose your preferred provider and set the corresponding environment variable:

Create your OpenAI API key here.

export OPENAI_API_KEY="your_key_here"

To associate your optimization runs with your Weco account and view them on the Weco dashboard, you can log in.

When you first run weco run, you'll be prompted if you want to log in/create an account (press l) or proceed anonymously (press Enter or s).
If you choose to login, this saves a Weco-specific API key locally (typically at ~/.config/weco/credentials.json).
If you choose to skip login, weco will still function using the environment variable LLM keys, but the run history will not be linked to a Weco account.

To log out and remove your saved Weco API key, use the following command:

weco logout

Once you've installed Weco and configured your API keys, you're ready to start optimizing your code:

Check out the Getting Started guide to learn how to use the Weco CLI
Check out the Writing Good Evaluation Scripts guide to learn how to write a good evaluation script
Check out the CLI Reference to learn more about the commands and options available
Visit the FAQ for answers to common installation and usage questions
Explore our Examples to see Weco in action