Introduction

Welcome to our workshop! In this workshop we'll be using the open-sourced IBM Granite AI foundation models for a number of use cases that demonstrates the value of generative AI.

By the end of this workshop, you will be able to:

• Summarize a text document using text summarization
• Generate specific information from a large document using the RAG technique
• Predict future trends using time series forecasting
• Extract entities from an unstructured text document using entity recognition
• Multimodal RAG using a multimodal LLM (MLLM) on a PDF file with images.

About this workshop

The introductory page of the workshop is broken down into the following sections:

• Agenda
• Technology Used
• Credits

Agenda

Lab 0: Pre-work	Pre-work for the workshop
Lab 1: Document Summarization with Granite	Learn how to use an AI model to summarize a work of literature
Lab 2: Retrieval Augmented Generation (RAG) with Langchain	Learn how to generate specific information from a large document
Lab 3: Energy Demand Forecasting with Granite Timeseries (TTM)	Learn how to predict future trends using time series forecasting
Lab 4: Entity Extraction from text using Granite	Learn how to use an AI model to extract entities from unstructured text.
Lab 5: Multimodal RAG using Granite and Docling	Learn how to use AI models to generate specific information from unstructured PDFs with images.

Technology Used

The technology used in the workshop is as follows:

• Google Colab
• IBM Granite AI foundation models
• Jupyter notebooks
• LangChain
• Ollama
• Replicate

Credits

• BJ Hargrave
• Martin Hickey
• Ming Zhao
• The notebooks used in this workshop are versions of notebooks from the IBM Granite Community modified for the workshop needs