• png logo

Advanced Retrieval-Augmented Generation (RAG) for Large Language Models

Enhance AI models and scale your tech career with advanced RAG solutions from Pragmatic AI Labs.

Advanced Retrieval-Augmented Generation (RAG) for Large Language Models

  • 5 weeks

  • 2 hours per week

  • Accreditation available

  • Digital certificate when eligible

  • Advanced level

Find out more about how to join this course

The CPD Certification Service

This course has been certified by the CPD Certification Service as conforming to continuing professional development principles. Find out more.

Learn to build RAG systems from scratch and lead LLMs with advanced solutions

Give yourself a leg up in the competitive world of tech by upskilling in one of AI’s most applied techniques: Retrieval-Augmented Generation (RAG).

On this five-week course from Pragmatic AI Labs, you’ll dive into the essential concepts and hands-on skills needed to master RAG and apply them in AI engineering for real-world solutions.

Apply advanced embedding strategies and chunking solutions

You’ll begin this course by exploring the basics of RAG, navigating its core processes and identifying its common pitfalls. With this foundation, you’ll soon move on to learning more advanced techniques, like document embedding and chunking.

Working through hands-on labs, you’ll apply these techniques to real-world data, experimenting with embedding models and refining your chunking strategies to improve document retrieval and alignment.

Create hybrid search systems

Next, you’ll dive into hybrid search in RAG, where you’ll learn how to combine semantic and keyword search to enhance retrieval performance.

You’ll work with both sparse indexing and dense encoding, mastering techniques like BM25 and Sentence Transformers to refine search results.

Plus, you’ll explore reranking strategies, using cross-encoders to improve the alignment of documents with user queries and boost retrieval accuracy.

Design multimodal retrieval applications

By the final week, you’ll explore multimodal RAG for image-based documents. You’ll integrate image encoders, apply quantisation for optimised storage, and build efficient indexing systems.

Through practical exercises and guided labs, you’ll create image embeddings using advanced models, improving search accuracy and optimising vector databases for efficient multimodal systems.

Syllabus

  • Week 1

    Introduction and Simple RAG Application

    • Course Introduction

      In the first video we present the overview of the course, and the main challenges of successfully implementing AI applications in enterprise companies.

    • Hands-on labs and homework exercises instructions

      Instructions to setup Jupyter notebook environment to execute the hands-on labs and exercises notebooks.

    • Simple RAG Introduction

      Introduction video to simple RAG applications

    • Hands-on lab walkthrough

      Video walkthrough of the hands-on lab building a simple RAG application.

    • Issues with Simple RAG

      Discussion on the recall-precision trade-off and its impact on the performance of RAG applications.

    • Lesson Reflection, Homework Exercise, and Quiz

      Review of the key points of the week, homework exercise on simple RAG notebook, and end-week quiz.

  • Week 2

    Document Embedding

    • Embedding Introduction

      Introduction to text embedding

    • Embedding - Hands-on Lab

      Walkthrough of the hands-on lab on the various aspects of embedding including tokenization, vocabulary and embedding visualization.

    • Embedding Lesson Reflection and Quiz

      Lesson Reflection on the key terms and points covered in the lesson, and week-end quiz.

  • Week 3

    Document Chunking

    • Document Chunking Introduction

      Video presentation of the need for document splitting and chunking and the main methods used to perform it.

    • Chunking Hands-on Lab

      Video walkthrough of the hands-on on Semantic Chunking, one of the popular chunking methods.

    • Chunking Overview

      Deeper overview of chunking strategies

    • Contextual Indexing - Hands-on Lab

      Hands-on lab to chunking enrichment using document context and LLM models.

    • Query-Document Alignment

      Discussion of the issue of misalignment of users' queries and document chunks.

    • Hands-on Lab - Reverse Hyde

      Hands-on lab on a powerful method to generate hypothetical questions for document chunks to improve query-document alignment.

    • Document Chunking Lesson Reflection

      Summary and review of the main key terms and points discussed this week.

    • Homework Exercise for Document Chunking

      Advanced exercise notebook to practice various topics and methods of document chunking.

    • Document Chunking Lesson Quiz

      Quiz to test the understanding of the main topics of document chunking.

  • Week 4

    Hybrid Search in RAG

    • Hybrid Search Introduction

      Introduction to Hybrid Search in RAG application to improve document recall in the retrieval step.

    • Hands-on Lab - Hybrid Search

      Hands-on lab to implement Hybrid Search in RAG application using sparse index with BM25.

    • Hands-on Lab - Reranking

      Hands-on lab to implement reranking of Hybrid-Search results in RAG application using a cross-encoder.

    • Hybrid Search Lesson Reflection

      Summary of key terms and points from the Hybrid Search lessons.

    • Homework Exercise - Hybrid Search

      Homework exercise to implement a more sophisticated Hybrid Search using SPLADE and Cohere reranking models.

    • Hybrid Search Quiz

      Quiz on the hybrid search week topics.

  • Week 5

    Multimodal RAG system to handle image based documents

    • Multimodal RAG Introduction

      Video introduction presentation of building RAG application for image based documents using Multimodal techniques.

    • Multimodal RAG Hands-on Lab

      Hands-on lab of building a multimodal RAG application on image based documents.

    • Multimodal RAG Lesson Reflection

      Overview of the main key points and terms covered in the Multimodal week.

    • Multimodal RAG Quiz

      Test on the main topics covered in the Multimodal week lesson.

Who is this accredited by?

The CPD Certification Service
The CPD Certification Service:

The CPD Certification Service was established in 1996 and is the leading independent CPD accreditation institution operating across industry sectors to complement the CPD policies of professional and academic bodies.

When would you like to start?

Start straight away and join a global classroom of learners. If the course hasn’t started yet you’ll see the future date listed below.

  • Available now

Learning on this course

On every step of the course you can meet other learners, share your ideas and join in with active discussions in the comments.

What will you achieve?

By the end of the course, you‘ll be able to...

  • Improve AI applications based on Large Language Models (LLM) using Retrieval-Augmented-Generation (RAG) advanced techniques.
  • Assess best use cases for RAG vs traditional GenAI

Who is the course for?

This course is for AI engineers, MLOps professionals, software developers, and data scientists eager to master advanced RAG systems and LLM applications. It’s perfect for those looking to expand their AI skills, integrate cutting-edge technologies into enterprise solutions, or transition into AI development roles.

Who will you learn with?

Who developed the course?

Pragmatic AI Labs

Learn from leading instructors from top universities with real-world industry experience.

Achieve your goals with practical courses designed with a vocational focus. Our engaging programs provide you with the knowledge and tools to succeed in your career and have a positive impact.

Ways to learn

Subscribe & save

Buy this course

Start learning today

Choose the best way to learn for you!

$349.99 for one year

Automatically renews

$79/one-off payment

Free

Develop skills to further your careerFulfill your current learning needTry this course - with limits
Access to this courseticktick

Limited to 5 weeks

Access to 1,000+ coursestickcrosscross
Learn at your own paceticktickcross
Discuss your learning in commentstickticktick
Tests to check your learningticktickcross
Certificate when you're eligibleDigital onlyPrinted and digitalcross
Continue & Upgrade

Cancel for free anytime

Ways to learn

Choose the best way to learn for you!

Buy this course

$79/one-off payment

Fulfill your current learning need

  • Access to this course
  • Learn at your own pace
  • Discuss your learning in comments
  • Tests to boost your learning
  • Printed and digital certificate when you’re eligible

Subscribe & save

$349.99 for one year

Automatically renews

Develop skills to further your career

  • Access to this course
  • Access to 1,000+ courses
  • Learn at your own pace
  • Discuss your learning in comments
  • Tests to boost your learning
  • Digital certificate when you're eligible

Cancel for free anytime

Start learning today

Free

Try this course - with limits

  • Limited to 5 weeks

Find out more about certificates, Unlimited or buying a course (Upgrades)

Learning on FutureLearn

Your learning, your rules

  • Courses are split into weeks, activities, and steps to help you keep track of your learning
  • Learn through a mix of bite-sized videos, long- and short-form articles, audio, and practical activities
  • Stay motivated by using the Progress page to keep track of your step completion and assessment scores

Join a global classroom

  • Experience the power of social learning, and get inspired by an international network of learners
  • Share ideas with your peers and course educators on every step of the course
  • Join the conversation by reading, @ing, liking, bookmarking, and replying to comments from others

Map your progress

  • As you work through the course, use notifications and the Progress page to guide your learning
  • Whenever you’re ready, mark each step as complete, you’re in control
  • Complete 90% of course steps and all of the assessments to earn your certificate

Want to know more about learning on FutureLearn? Using FutureLearn

Do you know someone who'd love this course? Tell them about it...