The "Recipes" in the Granite Snack Cookbook showcase the essential capabilities of IBM Granite models, in bite-sized instructional notebooks.
- RAG
- Agentic RAG
- Travel planner Agent
- Prompt Declaration Language (PDL)
- Notebook that uses the PDL Jupyter Extension (Not compatible with Colab)
- Notebook that uses the PDL Python API (Not yet available in Colab, because the latter uses Python 3.10)
- Retrieval Augmented Generation (RAG) with Granite RAG 3.0 8b
- Notebook that uses Ollama (Not available in Colab, because it requires a local Ollama server.)
- Notebook that uses Hugging Face Transformers and PEFT Libraries (Not available in Colab, because it requires a >16GB memory)
For information about contributing to this repo, code of conduct guidelines, etc., see the community CONTRIBUTING and Code of Conduct guides. All commits require DCO-signoff (discussed here) and GPG or SSH signing (discussed here). The GitHub recommended code security settings are enforced on this public repository (which include the signing requirement).
For more background and a FAQ, please see the community wiki
The Granite Snack Cookbook's base license is CC BY 4.0.
Code in this repository, including in notebook cells, is licensed under Apache 2.0.
Any example datasets committed to this repository are licensed under CDLA Permissive 2.0.
All content in these repositories including code has been provided by IBM under the associated open source software license and IBM is under no obligation to provide enhancements, updates, or support. IBM developers produced this code as an open source project (not as an IBM product), and IBM makes no assertions as to the level of quality nor security, and will not be maintaining this code going forward.