W&B Weave
Weights & Biases (W&B) Weave is a framework for tracking, experimenting with, evaluating, deploying, and improving LLM-based applications. Designed for flexibility and scalability, Weave supports every stage of your LLM application development workflow:
- Tracing & Monitoring: Track LLM calls and application logic to debug and analyze production systems.
- Systematic Iteration: Refine and iterate on prompts, datasets, and models.
- Experimentation: Experiment with different models and prompts in the LLM Playground.
- Evaluation: Use custom or pre-built scorers alongside our comparison tools to systematically assess and enhance application performance.
- Guardrails: Protect your application with pre- and post-safeguards for content moderation, prompt safety, and more.
Integrate Weave with your existing development stack via the:
Weave supports numerous LLM providers, local models, frameworks, and third-party services.
Get started
Are you new to Weave? Set up and start using Weave with the Python quickstart or TypeScript quickstart.
Advanced guides
Learn more about advanced topics:
- Integrations: Use Weave with popular LLM providers, local models, frameworks, and third-party services.
- Cookbooks: Build with Weave using Python and TypeScript. Tutorials are available as interactive notebooks.
- W&B AI Academy: Build advanced RAG systems, improve LLM prompting, fine-tune LLMs, and more.