W&B Weave

Track, test, and improve language model apps with W&B Weave

W&B Weave is an observability and evaluation platform that helps you track, evaluate, and improve your LLM application. With Weave, you can:

• Observe and debug your LLM application
• Evaluate your application’s responses using scorers and LLM judges

Get Started

W&B Weave provides Python and TypeScript libraries.

To install the Weave library, run the following command:

First install the Weave library:

Python

pip install weave

To start using the Weave library, create a Weights & Biases (W&B) account and obtain a copy your API key. The API key allows you to authenticate to your W&B account and start sending data to it.

Next Steps

Once you have completed the steps above, see the following quickstarts to learn how to add Weave to your code:

• Track LLM inputs & outputs
• Learn Weave with W&B Inference
• Get started evaluating your app
• Evaluate a RAG application.