Catalogue
/
Artificial Intelligence and Applied AI
/
Retrieval-Augmented Generation (RAG) Fundamentals

Retrieval-Augmented Generation (RAG) Fundamentals

A practical two day introductory course for participants who are new to Retrieval-Augmented Generation and want to understand how AI systems can answer questions using trusted external information. The agenda introduces the RAG workflow, document preparation, chunking, embeddings, vector search, retrieval, prompt construction, answer generation, and basic evaluation. The course focuses on building a clear conceptual and practical foundation without moving into advanced retrieval architectures or production scale optimization.

What will you learn?

You will learn how a basic RAG system connects a language model with external documents and data sources. You will understand how content is prepared, converted into embeddings, stored for retrieval, matched to user questions, and passed to a language model as context. You will also learn how to evaluate simple RAG systems and recognize common limitations such as poor retrieval, irrelevant context, and unsupported answers.

  • Understand the main components and workflow of a RAG system
  • Prepare documents for retrieval using chunking and metadata
  • Understand embeddings, vector search, and basic retrieval concepts
  • Evaluate simple RAG responses for relevance, accuracy, and grounding

Requirements:

  • Suitable for participants who are new to Retrieval-Augmented Generation
  • Basic familiarity with generative AI and large language models is helpful
  • General understanding of documents, databases, or search concepts is useful
  • No previous RAG experience required

Course Outline*:

*We customize the course outline and content to your specific needs and relevant use cases.

Module 1: Introduction to Retrieval-Augmented Generation

  • Understanding what RAG is and which problems it is designed to address
  • Comparing model only responses with responses grounded in external information
  • Understanding the basic sequence from user question to retrieval and generated answer
  • Exploring common use cases such as internal knowledge search, document assistants, and support systems

Module 2: Documents, chunking, and metadata

  • Preparing documents and text sources for use in a RAG system
  • Understanding why long documents are divided into smaller chunks
  • Comparing simple chunking approaches such as fixed size and structure based splitting
  • Using metadata to preserve information such as source, title, category, or date

Module 3: Embeddings and vector representations

  • Understanding embeddings as numerical representations of meaning
  • Comparing keyword search with semantic similarity search
  • Understanding how document chunks and user questions are represented as vectors
  • Introducing vector stores and their role in a basic RAG architecture

Module 4: Retrieval and similarity search

  • Understanding how a user query is matched against stored document vectors
  • Working with top matching chunks and simple similarity scores
  • Understanding the effect of retrieval depth on the amount of context returned
  • Recognizing common retrieval problems such as irrelevant or missing results

Module 5: Building context for the language model

  • Combining retrieved chunks into a useful context for generation
  • Writing simple prompts that instruct the model to use retrieved information
  • Asking the model to stay within the provided context when evidence is limited
  • Understanding how context length and irrelevant information can affect answer quality

Module 6: Generating grounded answers

  • Connecting retrieval results to a language model
  • Producing answers based on retrieved documents rather than model memory alone
  • Including source information or citations where appropriate
  • Handling situations where the retrieved information is insufficient to answer confidently

Module 7: Basic RAG evaluation

  • Evaluating whether the retrieved content is relevant to the user question
  • Checking whether generated answers are supported by the retrieved evidence
  • Identifying retrieval failures separately from generation failures
  • Using a small set of representative questions to assess overall system quality

Module 8: Limitations, security, and next steps

  • Understanding that RAG can reduce but not eliminate unsupported or incorrect answers
  • Considering permissions, sensitive information, and access to source documents
  • Recognizing risks from outdated, duplicated, or low quality content
  • Building a practical checklist for planning a simple RAG application

Hands-on learning with expert instructors at your location for organizations.

3,072€*
Graph Icon - Education X Webflow Template
Level:
intermediate
Clock Icon - Education X Webflow Template
Duration:
14
Hours (days:
2
)
Camera Icon - Education X Webflow Template
Training customized to your needs
Star Icon - Education X Webflow Template
Immersive hands-on experience in a dedicated setting
*Price can range depending on number of participants, change of outline, location etc.

Master new skills guided by experienced instructors from anywhere.

2,037€*
Graph Icon - Education X Webflow Template
Level:
intermediate
Clock Icon - Education X Webflow Template
Duration:
14
Hours (days:
2
)
Camera Icon - Education X Webflow Template
Training customized to your needs
Star Icon - Education X Webflow Template
Reduced training costs
*Price can range depending on number of participants, change of outline, location etc.

Upcoming Sessions

12-13 Jan 2027
Amsterdam
2-3 Feb 2027
Zurich
6-7 May 2027
London
24-25 Jun 2027
Berlin
15-16 Jul 2027
Madrid

Can't find a suitable date? Get in touch and we'll arrange one that works for you.

We use cookies to improve site navigation, analyse how the site is used, and support our marketing. You can accept all cookies, reject non-essential ones, or choose individual categories. Read our Cookie Notice