Training course · RAG & LLM Applications · SQL & Databases

RAG & LLM Applications for SQL and Database Professionals

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 SQL & Databases. 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.

Databases are the memory of every application, and their performance, consistency and security determine whether entire systems succeed. AI coding assistants and agents support database developers and DBAs in writing complex queries, reading execution plans, designing schemas and index strategies and migrating between database platforms. They translate business questions into SQL, refactor sprawling stored procedures and generate test data. One principle still holds: a syntactically valid query is not necessarily a correct one, and an agent with write access to production data is a serious risk. In this course you learn to use AI productively with schema context, execution plans and tests, and to design access so that your data stays protected at all times.

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?

  • Database and SQL developers
  • Database administrators for PostgreSQL, SQL Server, Oracle or MySQL
  • Backend developers responsible for data models and ORM layers
  • Data engineers and analytics engineers
  • BI developers working with complex reporting queries

Typical challenges we address

  • Slow queries and load spikes whose causes are hidden in execution plans
  • Sprawling stored procedures and triggers without documentation or tests
  • Risky schema changes and migrations on live systems
  • Different SQL dialects during platform changes or in multi-database estates

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.
  • Optimise queries and indexes with AI support based on execution plans rather than guesswork.
  • Plan and test schema changes and database migrations using generated scripts and rollback strategies.
  • Design database access for AI agents securely, with least privilege, read replicas and traceable queries.

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: SQL & Databases
  • Optimising SQL queries
  • Designing and reviewing schemas
  • Refactoring stored procedures
  • Planning migrations safely
  • Translating dialects
  • Generating test data
Module 7 Data protection, quality & transfer to daily work
  • Databases often hold personal and business-critical data: you learn to give AI tools schemas and anonymised samples instead of production data, manage credentials securely and implement GDPR requirements such as data minimisation and deletion policies.
  • 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

Optimising SQL queries

Have execution plans from EXPLAIN ANALYZE or Query Store interpreted, identify bottlenecks such as full table scans or poor join orders and get rewritten queries and suitable indexes with a clear rationale.

Designing and reviewing schemas

Derive normalised data models with keys, constraints and data types from requirements, review existing schemas for redundancy and missing integrity rules and generate ER diagrams.

Refactoring stored procedures

Explain large PL/SQL or T-SQL procedures, convert cursor loops into set-based logic, standardise error handling and add tests with frameworks such as tSQLt or pgTAP.

Planning migrations safely

Generate versioned migration scripts for Flyway or Liquibase, design zero-downtime strategies such as expand and contract and assess rollback paths as well as effects on locking and replication.

Translating dialects

Migrate queries, functions and data types between Oracle, SQL Server, PostgreSQL and MySQL, account for differences in date functions, sequences and transaction behaviour and test for identical results.

Generating test data

Create realistic synthetic datasets that respect constraints, distributions and edge cases without using personal production data, for load tests and development environments. Generators live in the repository under version control.

Possible hands-on projects

Slow query analyser

A script that processes the slow query log or statistics views, groups the most expensive queries and reports concrete index and rewrite suggestions.

Schema documentation generator

A tool that reads a database schema and produces searchable documentation with table descriptions, relationships and an ER diagram. It refreshes automatically after each migration.

Text-to-SQL assistant

A small web app with read-only access to a reporting database that turns business questions into checked SQL and shows both query and result transparently.

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 write SQL regularly, understand joins, aggregations and indexes and work with at least one relational database system.

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

Databases often hold personal and business-critical data: you learn to give AI tools schemas and anonymised samples instead of production data, manage credentials securely and implement GDPR requirements such as data minimisation and deletion policies.

Suggested dates

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

  • Mon, 23 November 2026 – Tue, 24 November 2026 Online Request
  • Thu, 3 December 2026 – Fri, 4 December 2026 Kaiserslautern Request
  • Wed, 9 December 2026 – Thu, 10 December 2026 Online Request
  • Wed, 16 December 2026 – Thu, 17 December 2026 Bremen Request
  • Wed, 13 January 2027 – Thu, 14 January 2027 Online Request
  • Tue, 19 January 2027 – Wed, 20 January 2027 Salzburg 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.

Should an AI agent access our database directly?

It can, but it needs careful planning. We recommend a dedicated read-only user, access to replicas or development databases rather than production, query timeouts and logging of every statement. Write changes go through versioned migration scripts with review. In the course you build exactly this safeguard, for instance through a restricted MCP server.

How reliable is AI-generated SQL?

It is usually syntactically correct, but semantic quality depends heavily on context: without the schema, relationships and business definitions, wrong joins or double counting creep in easily. With schema context, example queries and tests against known results, reliability rises considerably. You learn to validate generated queries systematically.

How much does “RAG & LLM Applications for SQL and Database Professionals” 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 SQL and Database Professionals

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