Open-Source AI Cookbook

The Open-Source AI Cookbook is a collection of notebooks illustrating practical aspects of building AI applications and solving various machine learning tasks using open-source tools and models.

Latest notebooks

Check out the recently added notebooks:

• Evaluating AI Search Engines with judges - the open-source library for LLM-as-a-judge evaluators
• Structured Generation from Images or Documents Using Vision Language Models
• Vector Search on Hugging Face with the Hub as Backend
• Multi-Agent Order Management System with MongoDB
• Scaling Test-Time Compute for Longer Thinking in LLMs
• Signature-Aware Model Serving from MLflow with Ray Serve

You can also check out the notebooks in the cookbook’s GitHub repo.

Contributing

The Open-Source AI Cookbook is a community effort, and we welcome contributions from everyone! Check out the cookbook’s Contribution guide to learn how you can add your “recipe”.

< > Update on GitHub