Training course · RAG & LLM Applications · Node.js Back End

RAG & LLM Applications for Node.js Back-End 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

“RAG & LLM Applications for Node.js Back-End Developers” is a hands-on course for roles such as Back-end developers using Express, Fastify or NestJS, Full-stack developers responsible for API layers and Developers building serverless functions and integration services. Rather than learning RAG & LLM Applications in the abstract, you work on tasks from your daily routine – with examples, exercises and templates from Node.js Back End.

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.

For many teams, Node.js is the backbone of REST and GraphQL APIs, real-time services, serverless functions and integration layers. Typical back-end work follows recurring patterns: routes and validation, database access with Prisma, Drizzle or TypeORM, authentication, error handling, logging and tests against real dependencies. AI coding assistants and agents handle these patterns reliably once they understand the project architecture. They generate endpoints from OpenAPI specifications, migrate Express applications to modular structures, write integration tests with Testcontainers and analyse memory leaks or event-loop-blocking operations. This course teaches you to use agents in a way that keeps security, observability and maintainability firmly intact.

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?

  • Back-end developers using Express, Fastify or NestJS
  • Full-stack developers responsible for API layers
  • Developers building serverless functions and integration services
  • Software architects designing Node.js-based microservices

Typical challenges we address

  • Organically grown Express apps with no clear layering and scattered error handling
  • Insufficient input validation and weaknesses in authentication and authorisation
  • Performance issues caused by blocking code or memory leaks that are hard to diagnose
  • Missing integration tests against databases, queues and external APIs

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.
  • Have AI agents build endpoints, data layers and integration tests that fit your Node.js architecture.
  • Use AI to analyse performance problems, memory leaks and security weaknesses in the back end.
  • Define guardrails so that generated back-end code meets your standards for validation, logging and error handling.

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: Node.js Back End
  • API endpoints from specifications
  • Database access and migrations
  • Integration tests with Testcontainers
  • Restructuring Express applications
  • Analysing performance and memory leaks
  • Security hardening
Module 7 Data protection, quality & transfer to daily work
  • Back ends often process personal data: production data, logs and database dumps should never go into prompts unfiltered, and credentials from environment variables must stay excluded. Vet new npm dependencies for supply-chain risk and licensing, and for critical services take the security requirements of NIS2 into account.
  • 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

API endpoints from specifications

From an OpenAPI or GraphQL schema, the agent generates routes or resolvers, validation with Zod or class-validator, service layers and consistent error responses – all matching your existing project structure.

Database access and migrations

The AI models schemas for Prisma, Drizzle or TypeORM, writes migrations, optimises queries with indexes and transactions and explains the impact on existing data before rollout.

Integration tests with Testcontainers

The assistant writes tests that spin up real databases, Redis or message brokers in containers, seed data and exercise API endpoints end to end with Supertest against realistic dependencies.

Restructuring Express applications

Monolithic Express projects are split into modules with controllers, services and repositories, middleware is standardised and callback code moved to async/await – backed by existing and new tests.

Analysing performance and memory leaks

The AI interprets heap snapshots, profiler output and logs, identifies operations blocking the event loop and proposes fixes such as streams, worker threads or caching.

Security hardening

The agent reviews authentication flows using JWTs or sessions, adds rate limiting, secure HTTP headers and input validation and checks the code against the OWASP API security risks.

Possible hands-on projects

Webhook relay service

A Fastify service that receives webhooks from various SaaS providers, verifies signatures, queues events and forwards them to internal systems with retry logic.

Job queue with dashboard

A background-processing service built on BullMQ and Redis, with retry strategies, a monitoring UI and integration tests. Failed jobs can be inspected and retried directly from the UI.

API gateway prototype

A lean gateway service with authentication, rate limiting, request logging and routing to several back-end services, developed entirely by an AI agent.

Prerequisites

Solid programming skills in Python (or TypeScript as an alternative), basic knowledge of databases and REST APIs, and some experience with LLM APIs. Back-end development experience with Node.js and JavaScript or TypeScript, plus a working knowledge of databases, HTTP 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

Back ends often process personal data: production data, logs and database dumps should never go into prompts unfiltered, and credentials from environment variables must stay excluded. Vet new npm dependencies for supply-chain risk and licensing, and for critical services take the security requirements of NIS2 into account.

Suggested dates

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

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Wed, 9 December 2026 – Thu, 10 December 2026 Bremen Request
  • Thu, 14 January 2027 – Fri, 15 January 2027 Online Request
  • Tue, 19 January 2027 – Wed, 20 January 2027 Salzburg Request
  • Mon, 1 February 2027 – Tue, 2 February 2027 Online Request
  • Tue, 16 February 2027 – Wed, 17 February 2027 Kaiserslautern 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.

Is the course suitable for both NestJS and Express?

Yes. We work with framework-neutral principles such as layering, validation and testability, and show with examples how to capture the conventions of Express, Fastify or NestJS in instruction files. That way the assistant generates code that fits your framework and your project structure rather than generic boilerplate.

How do I stop the AI from producing insecure back-end code?

Through clear rules, automated checks and critical review. On the course you define security rules for validation, authentication and data access, plug in static analysis and dependency scanning, and learn to spot typical weaknesses in generated code, such as missing authorisation checks or unsafe queries.

How much does “RAG & LLM Applications for Node.js Back-End 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 Node.js Back-End 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