Granite Language
Agentic RAG
Agentic RAG
Use Granite to answer complex queries using external information.View Notebook
Travel planner agent
Travel planner agent
Use Granite with LangChain to build a travel planner agent that can answer complex queries about planning a trip.View Notebook
Function-calling
Function-calling
Interpret customer queries, interact with APIs, and perform real-time data operations on a database through function-calling capabilities with Granite.View Notebook
Fine-tuning pirate style
Fine-tuning pirate style
Fine-tune Granite on a custom ‘pirate-talk’ dataset using the qLoRA (Quantized Low-Rank Adaptation) technique.View Notebook
PDL stand-alone or from a Python SDK
PDL stand-alone or from a Python SDK
Get started with PDL and Granite.View Examples
Docling RAG
Docling RAG
Use Granite to build an AI-powered document retrieval system with Docling.View Notebook
LangChain RAG
LangChain RAG
Use Granite to build a RAG system with LangChain.View Notebook
Granite Guardian
Get started guide
Get started guide
Get started with Granite Guardian to identify potential risks in prompts and responses across dimensions.View Notebook
Detailed Guide
Detailed Guide
Explore in-depth various use cases that highlight different risk in prompts and responses across various risk dimensions of our taxonomy.View Notebook
HAP detection
HAP detection
Use Granite Guardian to detect hate, abuse, and profanity, either in a prompt, the output, or both.View Notebook
Usage governance workflow
Usage governance workflow
Use Granite Guardian with IBM’s AI Risk Atlas to evaluate the risk profile of a potential AI use case.View Notebook
Granite Time Series
Get started guide
Get started guide
Get started with Granite Time Series running locally.View Notebook
Get Started with watsonx AI SDK
Get Started with watsonx AI SDK
Use the watsonX SDK to perform inference calls against a model hosted remotely on watsonX.View Notebook
Few-shot fine-tuning and evaluation
Few-shot fine-tuning and evaluation
Use Granite Time Series TTM for few-shot forecasting on an energy demand dataset.View Notebook
Zero-shot inference with exogenous data
Zero-shot inference with exogenous data
Use Granite Time Series with zero-shot inference and fine-tuning to forecast bike sharing demand.View Notebook