onedevatlasBeta
Browse the atlas
AllBTPCAPUI5ABAP
SampleSampletypeA worked example you read or clone. Evidence: it demonstrates, it never provides.See every one →What this type is →by SAPby SAPoriginPublished by SAP itself. A visible facet, never an input to a reading — a dormant official plugin reads exactly like a dormant independent one.See every one →Reference

teched2025-DA261

An SAP TechEd 2025 hands-on workshop on SAP HANA Cloud's AI capabilities: outlier analysis, text embeddings with machine learning, and the knowledge graph engine.

Three main exercises, each worked in a Jupyter notebook from a Python environment in SAP Business Application Studio against a connected SAP HANA Cloud instance, with the Python Machine Learning client generating the SQL: outlier analysis on financial transaction data with Isolation Forests, including a data-parallel variant; consumer complaints explored with HANA dataframes and classified by an AutoML model that predicts a company's monetary relief; and RDF triples created, queried with SPARQL and validated with SHACL in the knowledge graph engine, which the README reads for SQL-SPARQL interoperability. Sentiment through text analysis and similarity search over the complaint narratives with the vector engine and the text embedding model are marked optional add-ons. Getting Started comes first and the three main exercises can then be taken in any order; the systems are the ones the in-person workshop provides.

GitHub8 ★

Facts

Last pushLicenceApache-2.0

Where it sits

Lives in
BTP/BAIP
Demonstrates
Retrieval-augmented generationBTPRetrieval-augmented generationcapabilityGrounding a model's answer in data retrieved at question time: text split into chunks, each chunk embedded as a vector, and the chunks nearest to the question placed into the prompt. Semantic search is the same retrieval with a person reading the matches, and fine-tuning changes the model's weights, not its input.Predictive modelsBTPPredictive modelscapabilityTraining, deploying and calling a model that predicts a value from tabular business data: a classification, a regression, a forecast. Distinct from [LLM integration](capability:llm-integration), where a language model generates text, even where both run on the same service.Graph, spatial and document dataBTPGraph, spatial and document datacapabilityStoring and querying data that is not plain rows, such as a network of relationships, a geometry or a JSON document, in the database that already holds the rows instead of in a separate store per model. Free-text search over entities is [search](capability:search); similarity over embeddings is [retrieval-augmented generation](capability:retrieval-augmented-generation).
Requires
SAP HANA CloudSAP HANA Cloudartifactthe database every exercise runs against; the notebooks generate SQL for execution in the connected instance.SAP Business Application StudioSAP Business Application Studioartifactwhere the Python environment and the notebooks are; configuring it is part of the getting-started exercise.

Who is behind it

SAP SamplesSAP SamplesOrganisationMaintains this
In the atlas: maintains 222@SAP-samplesmaintainerAjay SorengPersonContributes to this
In the atlas: contributes to 36@ajaysorengChristoph MorgenPersonContributes to this
In the atlas: contributes to 2@cmogShabana SamsudheenPersonContributes to this
In the atlas: contributes to 2@shabana313 contributors

What it declares

Every artifact

Type
Sample
Origin
By SAP
Use as
A reference

As a sample

Form
Workshop or CodeJam material

Connections5

Download
teched2025-DA261 connectionsteched2025-DA261PROVIDES→ demonstrates3demonstrates authoredGraph, spatial and document datademonstrates authoredPredictive modelsdemonstrates authoredRetrieval-augmented generationNEEDS→ needs2needs stated where the Python environment and the notebooks are; configuring it is part of the getting-started exercise. SAP-samples/teched2025-DA261 — README, Exercises: https://github.com/SAP-samples/teched2025-DA261 SAP-samples/teched2025-DA261 — Exercise 2, Getting started: https://github.com/SAP-samples/teched2025-DA261/blob/main/exercises/ex2/README.mdSAP Business Application Studioneeds stated the database every exercise runs against; the notebooks generate SQL for execution in the connected instance. SAP-samples/teched2025-DA261 — README, Overview: https://github.com/SAP-samples/teched2025-DA261 SAP-samples/teched2025-DA261 — Exercise 2, Getting started: https://github.com/SAP-samples/teched2025-DA261/blob/main/exercises/ex2/README.mdSAP HANA Cloud

README

quoted from SAP-samples/teched2025-DA261 under Apache-2.0, read
SAP-samples/teched2025-DA261/README.mdOn GitHub

DA261 - Unlocking AI-driven insights from your business data in SAP HANA Cloud

Description

This repository contains the material for the SAP TechEd 2025 Hands-on Workshop Unlocking AI-driven insights from your business data in SAP HANA Cloud (Session-ID DA261).

Overview

In this workshop you will learn how to utilize SAP HANA Cloud's AI capabilities for custom AI applications on SAP Business Technology Platform. Find out about tabular AI use cases served from the database, similarity search with the SAP HANA Cloud vector engine and the text embedding model, and creating, storing and querying RDF Triples using the new SAP HANA Cloud knowledge graph engine, highlighting the SQL-SPARQL interoperability.

Requirements

The technical requirements to complete the exercises in this repository, including hardware and software specifications are taken care of by the provided systems used for the in-person Hands-on Workshop. Required configuration tasks are outlined in the Getting Started - Prepare your working environment and tools section.

Exercises

Here is overview of the exercises to be completed during this Hands-on Workshop, additional add-on exercises are optional and marked respectively. The Getting Started - Prepare your working environment and tools should pursued first, the other main exercises 1, 2 and 3 can be pursued in order of personal interest.


Contributing

Please read the CONTRIBUTING.md to understand the contribution guidelines.

Code of Conduct

Please read the SAP Open Source Code of Conduct.

How to obtain support

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.

Reuse Badge

REUSE status

License

Copyright (c) 2025 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.

Apache-2.0, read

Details

Sources3
Added by handdiscovered herechecked
github.com/SAP-samples/teched2025-DA261tree, pushes, contributors, CIchecked
README.mdquoted, and what the entry declareschecked

Sources are graph entities: the same page may back several entries, and an unreachable source flags every row that rests on it.

Compatibility and provenance
discovered viaAdded by hand
first seen in the atlas
ecosystem and domainbtp, ai-and-agents
Contributors3
Ajay SorengChristoph MorgenShabana Samsudheen

From the repository’s contributor list, .

History in the atlas1
  1. First seen.
For your agent
Ref
artifact:sap-samples-teched2025-da261
JSON
/artifacts/sap-samples-teched2025-da261.json
MCP
Connecting an agent