Training course · RAG & LLM Applications · PHP & Laravel/Symfony

RAG & LLM Applications for PHP 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 PHP Developers” is designed for roles such as PHP developers working with Laravel or Symfony, Developers of e-commerce systems such as Shopware or Magento and Agency teams juggling many client projects in parallel and shows step by step how to use RAG & LLM Applications productively, safely and transparently in PHP & Laravel/Symfony – from the fundamentals to advanced workflows.

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.

PHP powers a large share of the web – from Laravel and Symfony applications to Shopware and Magento stores and bespoke platforms that have evolved over many years. As a result, modern framework projects frequently sit alongside legacy code without types, tests or Composer structure. AI coding assistants and agents help on both fronts: they write PHPUnit and Pest tests, bring code up to modern language standards with Rector, work through PHPStan findings level by level, generate Eloquent or Doctrine models with migrations and explain tangled legacy logic. The prerequisite is good context on framework conventions, coding standards and the test environment. This course teaches you to use agents so that modernisation becomes predictable and safe.

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?

  • PHP developers working with Laravel or Symfony
  • Developers of e-commerce systems such as Shopware or Magento
  • Agency teams juggling many client projects in parallel
  • Teams modernising legacy PHP applications

Typical challenges we address

  • Legacy code without type declarations, namespaces or automated tests
  • Laborious upgrades of PHP versions and major framework releases
  • Security risks from SQL injection, XSS and unsafe file uploads in old code
  • Tight deadlines on agency projects combined with high quality expectations

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 for tests, static analysis and upgrades in Laravel, Symfony and legacy projects.
  • Modernise legacy code incrementally and safely with AI support.
  • Recognise typical security flaws in generated and existing PHP code and fix them in a targeted way.

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: PHP & Laravel/Symfony
  • Generating PHPUnit and Pest tests
  • Raising PHPStan levels step by step
  • Upgrades with Rector
  • Building Laravel and Symfony features
  • Understanding and untangling legacy code
  • Finding security vulnerabilities
Module 7 Data protection, quality & transfer to daily work
  • PHP applications frequently process customer data from shops and portals, so database dumps and logs containing personal data must never go into prompts unfiltered. Check new Composer packages for licence and vulnerabilities, keep credentials from .env files out of context and, as an agency, agree contractually whether client code may be processed by AI services.
  • 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

Generating PHPUnit and Pest tests

The agent writes unit and feature tests for controllers, services and models, uses factories and database transactions, and runs the tests iteratively until they pass consistently.

Raising PHPStan levels step by step

The AI works through static analysis findings systematically, adds type declarations, generics annotations and return types, and raises the analysis level in controlled steps without changing behaviour.

Upgrades with Rector

Rector rules are configured and run, remaining incompatibilities in PHP or framework upgrades are fixed by hand and deprecations surfaced in logs and tests are cleared systematically.

Building Laravel and Symfony features

From a functional description, the assistant creates migrations, Eloquent or Doctrine entities, form requests or validators, controllers, policies and tests – all in line with framework conventions.

Understanding and untangling legacy code

The assistant explains procedural legacy logic, extracts functions into namespaced classes and introduces Composer autoloading, laying the groundwork for further modernisation. Characterisation tests pin down the existing behaviour first.

Finding security vulnerabilities

The AI checks code for unsafe SQL queries, missing output escaping, CSRF gaps and insecure uploads, replacing problem areas with prepared statements and built-in framework mechanisms.

Possible hands-on projects

Laravel admin panel

A small management back end with authentication, roles, CRUD screens and feature tests, built by an AI agent from a short specification.

Symfony console importer

A Symfony console command that validates CSV or XML data, imports it into Doctrine entities and logs errors in a clear, readable way.

Upgrade readiness check

A script that runs PHPStan, a Rector dry run and Composer audit against a PHP project and produces a plain-language report on upgrade effort.

Prerequisites

Solid programming skills in Python (or TypeScript as an alternative), basic knowledge of databases and REST APIs, and some experience with LLM APIs. Solid PHP skills and experience with Laravel or Symfony, Composer 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

PHP applications frequently process customer data from shops and portals, so database dumps and logs containing personal data must never go into prompts unfiltered. Check new Composer packages for licence and vulnerabilities, keep credentials from .env files out of context and, as an agency, agree contractually whether client code may be processed by AI services.

Suggested dates

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

  • Tue, 24 November 2026 – Wed, 25 November 2026 Online Request
  • Mon, 30 November 2026 – Tue, 1 December 2026 Munich Request
  • Thu, 10 December 2026 – Fri, 11 December 2026 Online Request
  • Thu, 14 January 2027 – Fri, 15 January 2027 Hanover Request
  • Mon, 25 January 2027 – Tue, 26 January 2027 Online Request
  • Mon, 1 February 2027 – Tue, 2 February 2027 Berlin 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 AI-assisted coding worthwhile for old PHP code without a framework?

That is exactly where it shines. AI assistants explain convoluted procedural logic, write characterisation tests that pin down existing behaviour and then introduce namespaces, autoloading and types step by step. This gives you a safe foundation for modernising legacy applications instead of attempting a risky full rewrite.

How should agencies handle client code and AI?

Agencies should agree with their clients contractually whether, and with which services, source code may be processed. On the course we discuss options such as business licences with no training on your data, exclusion rules for sensitive files and documented review processes that give your clients full transparency.

How much does “RAG & LLM Applications for PHP 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 PHP 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