Training course · RAG & LLM Applications · Kubernetes & Microservices

RAG & LLM Applications for Kubernetes and Microservices Teams

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 Kubernetes & Microservices. 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.

Kubernetes has become the standard platform for microservices – and with it comes a flood of YAML manifests, Helm charts, Kustomize overlays, operators, service mesh configuration and GitOps repositories. On top of that, failures are distributed across dozens of services. AI coding assistants and agents take a lot of that complexity off your hands: they generate Helm charts with sensible defaults, diagnose CrashLoopBackOff and OOMKilled errors from events and logs, write NetworkPolicies and RBAC rules on the least-privilege principle and help define service boundaries. At the same time, an agent with cluster access needs firm limits. This course teaches you to use AI for manifests, troubleshooting and architecture work without losing control of your clusters.

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?

  • Platform engineers and Kubernetes administrators
  • Developers running microservices on Kubernetes
  • Site reliability engineers with cluster responsibility
  • Software architects designing distributed systems
  • DevOps teams introducing or scaling GitOps

Typical challenges we address

  • Unwieldy amounts of YAML, Helm values and overlays across many environments
  • Difficult troubleshooting of distributed issues spanning services, networking and resource limits
  • Security gaps from overly broad RBAC, missing NetworkPolicies and privileged containers
  • Unclear service boundaries and tight coupling in growing microservice landscapes

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.
  • Create and review Helm charts, overlays and policies efficiently with AI agents.
  • Diagnose issues in clusters and microservices faster with structured AI support.
  • Restrict agents’ cluster access and enforce security and architecture rules consistently.

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: Kubernetes & Microservices
  • Creating Helm charts and Kustomize overlays
  • Debugging pods and deployments
  • RBAC and NetworkPolicies
  • Service boundaries and communication
  • Setting up observability
  • Maintaining GitOps repositories
Module 7 Data protection, quality & transfer to daily work
  • Kubeconfigs, service account tokens and secrets must never end up in prompts, and agents should only work with read-only or tightly scoped rights in non-production clusters. Check container images and charts for provenance, signatures and vulnerabilities, and take into account the supply-chain and SBOM requirements of NIS2 and the Cyber Resilience Act.
  • 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

Creating Helm charts and Kustomize overlays

The agent generates Helm charts or Kustomize overlays with probes, resource requests, pod disruption budgets and security contexts, validates them with helm lint and kubeconform and documents every value.

Debugging pods and deployments

From kubectl output, events and container logs, the AI narrows down causes of CrashLoopBackOff, OOMKilled, ImagePullBackOff or failing readiness probes and proposes concrete fixes. The team reviews every proposed fix before applying it.

RBAC and NetworkPolicies

The AI analyses existing roles and traffic flows, writes least-privilege RBAC rules and creates NetworkPolicies that allow only the traffic services genuinely need. Changes are tested in a non-production cluster first.

Service boundaries and communication

The assistant helps define service boundaries along business domains, weigh synchronous against asynchronous communication and implement patterns such as outbox, circuit breaker or saga properly.

Setting up observability

Services get OpenTelemetry instrumentation, Prometheus metrics, ServiceMonitors and alert rules, plus dashboards that make latency, error rate and saturation visible. Alerts are aligned with service level objectives so that only relevant incidents escalate.

Maintaining GitOps repositories

The AI structures repositories for Argo CD or Flux, separates environments cleanly, automates image updates and explains sync failures using status output and diffs. Drift between repository and cluster becomes visible.

Possible hands-on projects

Manifest linter with a rule set

A tool that checks Kubernetes manifests for missing limits, probes, labels and insecure settings and produces a report for pull requests.

Microservice demo with tracing

Two or three small services instrumented with OpenTelemetry, deployed via Helm to a local cluster, including a dashboard for distributed traces.

Cluster hygiene report

A CLI that finds unused ConfigMaps, orphaned PersistentVolumes and deployments without resource settings and suggests clean-up actions. Nothing is deleted without human approval.

Prerequisites

Solid programming skills in Python (or TypeScript as an alternative), basic knowledge of databases and REST APIs, and some experience with LLM APIs. Practical experience with containers, kubectl and core Kubernetes objects, plus a working knowledge of Helm, YAML and Git.

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

Kubeconfigs, service account tokens and secrets must never end up in prompts, and agents should only work with read-only or tightly scoped rights in non-production clusters. Check container images and charts for provenance, signatures and vulnerabilities, and take into account the supply-chain and SBOM requirements of NIS2 and the Cyber Resilience Act.

Suggested dates

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

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Thu, 10 December 2026 – Fri, 11 December 2026 Salzburg Request
  • Mon, 14 December 2026 – Tue, 15 December 2026 Online Request
  • Thu, 7 January 2027 – Fri, 8 January 2027 Online Request
  • Thu, 21 January 2027 – Fri, 22 January 2027 Bremen Request
  • Mon, 25 January 2027 – Tue, 26 January 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.

Should an AI agent have direct access to my cluster?

Only in a controlled way. For analysis and troubleshooting, read-only rights in selected namespaces are usually enough, while changes should go through GitOps repositories and reviews. On the course you set up dedicated service accounts, local test clusters and approval processes so the agent is useful without creating production risk.

Does the course also cover microservice architecture questions?

Yes. Beyond manifests and operations, we look at how AI can support defining service boundaries, weighing communication patterns and assessing architecture options. The AI provides options and arguments, while the decision stays with the team and is documented transparently. That keeps decisions accountable.

How much does “RAG & LLM Applications for Kubernetes and Microservices Teams” 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 Kubernetes and Microservices Teams

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