Training course · RAG & LLM Applications · SAP & ABAP

RAG & LLM Applications for SAP ABAP Developers

Develop RAG and LLM applications: embeddings, vector databases, chunking, retrieval, evaluation, cost control and data protection.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

This course connects RAG & LLM Applications with the everyday processes of SAP & ABAP. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

Retrieval-augmented generation connects language models to your own knowledge: manuals, contracts, tickets, wikis or product data are made searchable and handed to the model as context at runtime. The result is assistants that give grounded answers with citations instead of hallucinating. In this two-day course you build a complete RAG pipeline, from document preparation through embeddings and a vector database to answer generation, and you learn which levers actually determine quality.

Day two takes you from prototype to robust application. You compare chunking strategies, combine semantic and lexical search, apply reranking, metadata filters and query rewriting, and measure the effect with systematic evaluations. You also cover prompt caching, cost control, latency optimisation, document-level access control and privacy-compliant operation with an eye on GDPR and the EU AI Act. By the end you know when classic RAG is enough, when a large context window or agentic retrieval is the better option, and how to justify your architecture choices.

Few development landscapes carry as much accumulated logic as SAP. Custom reports, user exits, BAdIs and Z programmes built up over many years must be assessed, adapted or replaced with clean core extensions for S/4HANA. AI coding assistants and agents help you make sense of undocumented ABAP, resolve ABAP Test Cockpit findings, move classic ABAP to modern ABAP with CDS views and the RESTful Application Programming Model, and retrofit unit tests. Because ABAP is tightly woven into dictionary objects, customising and business processes, precise context and disciplined reviews are essential. In this course you learn to apply AI to analysis, refactoring and new development in SAP, aligned with your transport system, namespaces and the quality standards of your SAP operations.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • ABAP developers in in-house IT and SAP consultancies
  • SAP technical consultants and development architects
  • Teams working on S/4HANA conversion and clean core projects
  • SAP Basis and integration specialists who also write code
  • Fiori and RAP developers

Typical challenges we address

  • Large volumes of poorly documented Z code with unclear usage and many dependencies
  • Heavy adaptation effort for simplification items and data model changes during S/4HANA migration
  • Low test coverage because ABAP Unit was rarely used in legacy code
  • Skills shortages and knowledge loss when experienced developers leave

What you will be able to do

  • You build a complete RAG pipeline from document preparation to answers with citations.
  • You choose embedding model, chunking strategy and vector database on solid grounds.
  • You improve retrieval quality with hybrid search, reranking and metadata filters.
  • You measure application quality with systematic evaluations and detect regressions.
  • Use AI agents to systematically analyse, document and assess existing ABAP for S/4HANA.
  • Modernise classic ABAP in line with clean core principles and secure refactoring with generated ABAP Unit tests.
  • Integrate AI tools with ADT, abapGit and your transport and review process.

Course outline

Day 1

Module 1 Foundations of RAG and LLM applications
  • Anatomy of a RAG pipeline: ingestion, indexing, retrieval, generation
  • Understanding embeddings: semantic similarity, dimensions, model selection
  • Weighing RAG against fine-tuning and long context windows
  • Structured outputs, citations and dealing with hallucinations
Module 2 Document preparation and chunking
  • Reliably extracting PDFs, Office documents, HTML and tables
  • Chunking strategies: fixed size, structure-aware, semantic, with overlap
  • Enriching metadata and generating contextual summaries per chunk
  • Incremental updates and deletion of documents in the index
Module 3 Vector databases and retrieval strategies
  • Comparing vector databases and extensions such as pgvector, Qdrant, Weaviate or OpenSearch
  • Hybrid search combining vector and full-text search with BM25
  • Reranking, metadata filtering and query rewriting
  • Agentic retrieval: letting the model decide on search steps and tools
Module 4 Evaluation and quality assurance
  • Building and maintaining test sets from real user questions
  • Retrieval metrics such as recall and precision, and answer metrics such as faithfulness
  • Using and calibrating LLM-as-a-judge sensibly
  • Regression testing when chunking, model or prompt changes

Day 2

Module 5 Operations, cost and data protection
  • Prompt caching, batch processing and model choice to cut costs
  • Optimising latency and streaming responses
  • Document-level permissions, tenant isolation and protection against prompt injection
  • Data protection: data residency, processing agreements, deletion policies, GDPR and the EU AI Act
Module 6 Practice lab: SAP & ABAP
  • Analysing ABAP for S/4HANA
  • Documenting legacy code
  • Moving towards clean core
  • Retrofitting ABAP Unit
  • Resolving ATC findings
  • Building RAP and OData services
Module 7 Data protection, quality & transfer to daily work
  • ABAP code often contains business logic, pricing conditions and personal data structures: you learn to assess source code before sharing it with AI services, respect the licence and usage terms of your SAP contracts and comply with GDPR rules for test data.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Analysing ABAP for S/4HANA

Scan Z programmes for access to obsolete tables, changed data models and unreleased APIs, group findings by simplification item and generate concrete remediation proposals with effort estimates.

Documenting legacy code

Have undocumented reports, function modules and user exits explained, summarise programme logic in business terms and produce technical documentation and flow diagrams for knowledge transfer and audits.

Moving towards clean core

Convert classic modifications and SELECT loops into modern ABAP with inline declarations, CDS views and released APIs, and identify candidates for RAP-based side-by-side or developer extensibility.

Retrofitting ABAP Unit

Extract testable interfaces from existing classes, prepare test doubles for database access using the SQL test double framework and generate meaningful unit tests as a safety net for refactoring.

Resolving ATC findings

Prioritise messages from ABAP Test Cockpit and Code Inspector, detect performance issues such as nested SELECTs and propose compliant corrections with an explanation for code review.

Building RAP and OData services

Design CDS data models, behaviour definitions and service bindings from business requirements, implement validations and determinations and generate suitable Fiori elements annotations. The agent follows your naming conventions and package structure.

Possible hands-on projects

Z code inventory

A script that processes exported ABAP sources, classifies objects by usage, complexity and migration relevance and produces a prioritised overview for project planning.

Custom code explainer

A small web app where you paste a report and receive a business-level summary, its table dependencies and migration risks.

RAP scaffolder

A generator that creates CDS views, a behaviour definition and a service skeleton from a table definition, following your naming conventions.

Prerequisites

Solid programming skills in Python (or TypeScript as an alternative), basic knowledge of databases and REST APIs, and some experience with LLM APIs. You develop in ABAP on a regular basis and are familiar with ABAP Development Tools in Eclipse or the classic ABAP Workbench.

Technical requirements

A laptop with Python, Git, Docker and a code editor, plus API access to at least one LLM and embedding provider. Credentials for the exercises can be provided if needed.

Data protection & compliance

ABAP code often contains business logic, pricing conditions and personal data structures: you learn to assess source code before sharing it with AI services, respect the licence and usage terms of your SAP contracts and comply with GDPR rules for test data.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Mon, 23 November 2026 – Tue, 24 November 2026 Online Request
  • Mon, 30 November 2026 – Tue, 1 December 2026 Augsburg Request
  • Tue, 15 December 2026 – Wed, 16 December 2026 Online Request
  • Thu, 14 January 2027 – Fri, 15 January 2027 Online Request
  • Thu, 21 January 2027 – Fri, 22 January 2027 Kaiserslautern Request
  • Mon, 1 February 2027 – Tue, 2 February 2027 Online Request

Frequently asked questions

When is RAG better than fine-tuning?

RAG is the right choice when a model needs access to current, extensive or frequently changing knowledge and should cite its sources. Fine-tuning mainly changes style, format or specialised behaviour. In many projects RAG is the faster, cheaper and more controllable route, sometimes complemented by fine-tuning for niche tasks.

Which vector database should we use?

That depends on data volume, existing infrastructure, filtering needs and operating model. If you already run PostgreSQL, pgvector often takes you a long way, while specialised systems shine with large datasets and hybrid search. In the course you compare several options hands-on and derive criteria for your own decision.

How can RAG be run in a GDPR-compliant way?

Key factors are choosing providers with suitable data residency and a data processing agreement, enforcing document-level permissions, having a deletion policy for the index and logs, and minimising personal data. For highly sensitive data, self-hosted models are also an option. We work through these choices using realistic architectures.

Do AI assistants really understand ABAP?

Current models read and write ABAP competently, but they know nothing about your custom tables, customising or namespaces. Quality improves markedly when you supply dictionary definitions, interfaces and conventions as targeted context. In the course you practise exactly that, for example with sources exported via abapGit and project-specific rule files for the agent.

How does AI-generated code get into the SAP system?

A proven route runs through ADT or abapGit: the assistant works on exported sources or directly in the IDE, changes are reviewed, validated with ATC and ABAP Unit and transported as usual. This preserves the transport system, the four-eyes principle and traceability, and no agent ever writes to production systems unchecked.

How much does “RAG & LLM Applications for SAP ABAP Developers” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for SAP ABAP Developers

More RAG & LLM Applications courses

All 29 RAG & LLM Applications courses

RAG & LLM Applications · MunichRAG & LLM Applications · SalzburgRAG & LLM Applications · BerlinRAG & LLM Applications · AugsburgRAG & LLM Applications · HanoverRAG & LLM Applications · BremenRAG & LLM Applications · StuttgartRAG & LLM Applications · KaiserslauternRAG & LLM Applications · Online