This repository contains the material for the SAP TechEd 2025 session called AI167 - Ground your AI in business context: A hands-on with document grounding.
In this hands-on session, we will explore how to make Large Language Models truly enterprise-ready by grounding them with your own business data using Grounding in SAP GenAI Hub. Throughout this lab, you will learn how to:
- Build and manage data repositories for grounding.
- Create embeddings using the Vector API.
- Process full documents using the Pipeline API.
- Retrieve relevant context with the Retrieval API.
- Apply grounding end-to-end using the Orchestration layer in SAP GenAI Hub.
By the end of this session, you will have hands-on experience turning an LLM from a general-purpose assistant into a trusted, context-aware enterprise AI system that answers based on your data — not guesses. So get ready — this is where ideas get real.
The requirements to follow the exercises in this repository are:
- Visual Code Studio
- Bruno
- Exercise 1 - Setup Python Environment
- Exercise 2 - Get started with Grounding
- Exercise 3 - Ground your LLM with Custom Documents
Please read the CONTRIBUTING.md to understand the contribution guidelines.
Please read the SAP Open Source Code of Conduct.
Support for the content in this repository is available during the actual time of the online session for which this content has been designed. Otherwise, you may request support via the Issues tab.
Copyright (c) 2024 SAP SE or an SAP affiliate company. All rights reserved. This project is licensed under the Apache Software License, version 2.0 except as noted otherwise in the LICENSE file.