Skip to content
  1. Home
  2. Guides and documents
  3. Open-Source AI Cookbook

Open-Source AI Cookbook

Community notebooks for building with open models and tools

What it is

Hugging Face's community-driven cookbook, also published on the Hub's Learn pages. Notebooks show end-to-end work with open-source models and libraries: advanced RAG, agents for data analysis and text-to-SQL, fine-tuning code models, dataset cleaning with LLM judges, code search and benchmarking inference servers.

Good for

  • Build RAG with open-source models
  • Fine-tune a model on a single GPU
  • Create a text-to-SQL agent

What you need

Python and Jupyter; a GPU or Hugging Face account for some notebooks

Worth knowingWritten by many contributors, so depth and upkeep differ from one notebook to the next.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for data & research

See the topic →
  • Advanced RAG Techniques

    NirDiamant/RAG_Techniques

    40+ runnable notebooks on retrieval-augmented generation methods

    GuideGitHub stars: 30k
  • LLM Zoomcamp

    DataTalksClub/llm-zoomcamp

    Free ten-week course on RAG, vector search, agents and evaluation

    GuideGitHub stars: 7.7k
  • arXiv Search

    NousResearch/hermes-agent

    Search arXiv papers by keyword, author, category or ID

    SkillGitHub stars: 263k
  • Blocked Page Recovery

    NousResearch/hermes-agent

    Recover content when a fetch hits 403, a paywall or a bot wall

    SkillGitHub stars: 263k