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

Scale your tech career with cutting-edge AI applications to build advanced RAG systems and optimise LLMs with Pragmatic AI Labs.

Duration

5 weeks

Weekly study

2 hours

100% online

How it works

Unlimited subscription

Learn 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.

  • 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.

More courses you might like

Learners who joined this course have also enjoyed these courses.

©2025  onlincourse.com. All rights reserved