AI Engineering Bootcamp: RAG (Retrieval Augmented Generation) for LLMs

17h 53m 5s
English
Paid
This course will teach you how to create more intelligent AI applications using one of the most important techniques in modern artificial intelligence - Retrieval Augmented Generation (RAG). You will learn how to combine Large Language Models (LLMs) with RAG to develop advanced projects such as chatbots, financial analysis systems, and more.
Read more about the course

Why is RAG so important?

The limitations of many AI systems are related to their reliance on outdated data from their training samples. RAG addresses this issue by providing access to up-to-date information from external sources, including databases and documents. This makes AI more accurate and useful in real-world scenarios.

Example:

A chatbot in an online store can instantly check the current inventory based on real-time data, instead of relying on static training data, and give you an accurate answer about product availability and delivery times.

What you will learn:

  1. Basics of retrieval systems:
    • How to prepare textual data for search
    • Various search models (Boolean, vector, probabilistic)
    • Indexing, queries, and data ranking
  2. Basics of generative models:
    • Transformer architecture and attention mechanisms
    • Data preparation and text model training
  3. Introduction to Retrieval-Augmented Generation:
    • Combination of search and generation
    • Key principles and application of RAG in real tasks
  4. Working with OpenAI API:
    • API setup and effective use of prompts
    • Configuration parameters and their impact on model behavior
  5. Implementation of RAG with OpenAI:
    • Building fully functional RAG systems
    • Integrating search and generation to solve complex tasks
  6. Working with unstructured data:
    • Processing data from various formats: PDF, Word, PowerPoint, Excel, and images
    • Extracting valuable information from texts and multimedia
  7. Multimodal RAG systems:
    • Using textual and visual data to expand system capabilities
    • Integrating different types of data into a single response
  8. Agent systems with RAG:
    • Building AI agents capable of interacting with users and performing tasks
    • Managing agent states and dynamically executing tasks

Why do you need this course?

You will gain practical skills that will allow you to apply RAG in real projects and build scalable AI applications capable of processing complex queries and dynamically providing up-to-date answers.

Watch Online AI Engineering Bootcamp: RAG (Retrieval Augmented Generation) for LLMs

Join premium to watch
Go to premium
# Title Duration
1 Course Outline 08:12
2 Meet Rubber Ducky! Your AI Course Assistant using RAG 06:05
3 Overview: Fundamentals of Retrieval Systems 04:05
4 Overview of Information Retrieval 05:38
5 What is Tokenization? 07:21
6 OpenAI Tokenizer 06:13
7 Libraries and Data Handling for RAG 03:16
8 Tokenization Techniques 04:25
9 Preprocessing Steps 08:58
10 Types of Retrieval Systems 07:07
11 Vector Space Model (TF-IDF) 09:45
12 Implementing TF-IDF 06:08
13 TF-IDF Function and Output Analysis 07:57
14 Boolean Retrieval Model 03:58
15 Boolean Retrieval Implementation 16:57
16 Probabilistic Retrieval Model - Part 1 07:15
17 Probabilistic Retrieval Model - Part 2 07:29
18 How Google Search Works 11:30
19 Key Concepts: Indexing, Querying, and Ranking 07:23
20 What Did You Learn in This Section? 02:32
21 ReAct Prompt Engineering 11:53
22 Chain of Thought Prompt Engineering 14:25
23 Overview: Generative AI Fundamentals 01:47
24 Introduction to Text Generation 04:10
25 Understanding Transformers 12:48
26 Rock-Paper-Scissors, Dices and Strawberries 08:25
27 Text Generation with GPT2 12:52
28 Tokenization for Text Generation 06:01
29 Padding the Data for Consistency 05:06
30 Attention Mechanisms 06:15
31 Creating a Dataset Class 07:36
32 Fine-Tuning the GPT-2 Model 08:33
33 Generating Text with GPT-2 04:14
34 What Did You Learn in This Section? 01:40
35 LLMs, Few-shot, Scaling and Factuality 14:26
36 Overview: RAG Fundamentals 02:39
37 Introduction to RAG Architecture 05:18
38 Tokenization and Embeddings for RAG 13:16
39 FAISS Index: Efficient Similarity Search 04:16
40 Building a Retrieval System 07:45
41 Developing a Generative Model 11:01
42 Implementing the RAG System 07:01
43 Defining a Relevant Context Distance 11:40
44 Understanding Generation Model Parameters 06:23
45 Configuring RAG with Parameters 05:07
46 What Did You Learn in this Section? 03:10
47 LongRAG and LightRAG 16:41
48 Overview: Working with the OpenAI API 03:48
49 OpenAI API for Text 08:48
50 Setting Up OpenAI API Key 05:50
51 System Message and Parameters 15:00
52 OpenAI API Setup 04:32
53 Generating Text with OpenAI API 07:03
54 OpenAI API Parameters 10:21
55 OpenAI API for Images 08:15
56 With Image URL 04:55
57 Converting Images to Base64 03:50
58 Assess My Python Course Thumbnail 04:49
59 What Did You Learn in this Section? 03:51
60 Project Briefing: Customer Acquisition 06:08
61 OpenAI Setup 05:40
62 AI Agent System Prompt 08:22
63 Processing Images for GenAI 05:25
64 Extract Data with GenAI 13:39
65 Improving GenAI Extraction 06:19
66 GenAI with all Images 06:56
67 PDF to Images 10:32
68 Wrapping Up the OpenAI GenAI Project 08:17
69 Overview: RAG with OpenAI GPT Models 04:35
70 Case Study Briefing: Cooking Books 04:58
71 Converting PDF to Images 09:16
72 Reading a Single Image with GPT 12:04
73 Enhancing AI with Prompt Engineering 09:11
74 Reading All Images in a Dataset 05:08
75 Filtering Non-relevant Information 06:04
76 Understanding Embeddings in NLP 06:51
77 Generating Embeddings 13:57
78 Building FAISS Index and Metadata Integration 06:28
79 Implementing a Robust Retrieval System 14:42
80 Combining Outputs for Enhanced Results 02:57
81 Constructing a Generative Model 11:43
82 Complete RAG System Implementation 06:42
83 How to Improve RAG Systems Effectively? 07:04
84 Overview: Working With Unstructured Data 03:37
85 Introduction to Langchain Library 07:27
86 Excel Data: Best Practices for Data Handling 06:42
87 Python - Initial Setup for Data Processing 05:48
88 Loading Data and Implementing Chunking Strategies 05:14
89 Developing a Retrieval System for Unstructured Data 06:11
90 Building a Generation System for Dynamic Content 09:13
91 Building Retrieval and Generation Functions 09:58
92 Working with Word Documents 04:55
93 Setting Up Word Documents for RAG 06:18
94 Implementing RAG for Word Documents 02:27
95 Working with PowerPoint Presentations 04:45
96 PowerPoint Setup for RAG 04:12
97 RAG Implementation for PowerPoint 03:10
98 Working with EPUB Files 04:59
99 EPUB Setup for RAG 04:48
100 RAG Implementation for EPUB Files 02:23
101 Working with PDF Files 04:22
102 PDF Setup for RAG 05:52
103 RAG Implementation for PDF Files 05:38
104 What Did You Learn in This Section? 03:57
105 Exercise: Imposter Syndrome 02:57
106 Overview: Multimodal RAG 03:39
107 Introduction to Multimodal RAG 05:59
108 Setup and Video Processing 05:24
109 Extracting Audio from Video 08:45
110 Compressing Audio Files 04:18
111 Transcribing Audio with OpenAI Whisper 10:08
112 Whisper Model 06:32
113 Extracting Frames from Video 05:50
114 Introduction to Contrastive Learning 05:15
115 Understanding the CLIP Model 05:23
116 Tokenizing Text for Multimodal Tasks 08:14
117 Chunking and Embedding Text 11:37
118 Embedding Images for Multimodal Analysis 08:37
119 Understanding Cosine Similarity in Multimodal Contexts 06:47
120 Applying Contrastive Learning and Cosine Similarity 10:27
121 Visualizing Text and Image Embeddings 11:12
122 Query Embedding Techniques 04:13
123 Calculating Cosine Similarity for Query and Text 11:48
124 GenAI Model Setup for Multimodal Tasks 04:56
125 Building a GenAI Model 07:12
126 What Did You Learn in This Section? 02:13
127 Project Briefing: Starbucks Financial Data 05:28
128 Transcribing Audio with OpenAI Whisper 11:23
129 Embedding Transcription with CLIP 07:36
130 Converting PDF to Images 05:58
131 Embedding Images for Multimodal Analysis 04:59
132 Retrieval System 17:14
133 Preparing Context 05:00
134 Generative System 12:47
135 Overview: Agentic RAG 02:52
136 AI Agents 07:52
137 Agentic RAG 05:45
138 Setup and Data Loading 09:55
139 State Management and Memory in Agentic Systems 07:55
140 AgentState Class 04:30
141 Greeting the Customer 04:53
142 AI Agent that Checks the Question 10:48
143 AI Agent that Assesses the Validity of the question 07:23
144 Retrieving the Documents 05:47
145 Testing the App 07:14
146 Generate Answers 09:22
147 AI Agent that Improves the Answer 11:14
148 Asking User For More Questions 05:30
149 Agentic RAG Recap - Key Learnings and Next Steps 06:18
150 Thank You! 01:18

Similar courses to AI Engineering Bootcamp: RAG (Retrieval Augmented Generation) for LLMs

Deployment from Scratch

Deployment from ScratchJosef Strzibny

Category: Others, Python, Ruby
Duration
Build an AI Career Coach using an Open Source LLM

Build an AI Career Coach using an Open Source LLMzerotomastery.io

Category: Others
Duration 1 hour 38 minutes 53 seconds
System Design for Interviews and Beyond

System Design for Interviews and BeyondMikhail Smarshchok

Category: Others
Duration 7 hours 53 minutes 5 seconds
Building a Virtual Machine for Programming Language

Building a Virtual Machine for Programming LanguageudemyDmitry Soshnikov

Category: Others
Duration 4 hours 27 minutes 8 seconds
Writing for Developers. Blogs that get read
The World of Computer Networking. Your CCNA starts here

The World of Computer Networking. Your CCNA starts hereudemy

Category: Others
Duration 14 hours 40 minutes 24 seconds
AI for Beginners: Inside Large Language Models

AI for Beginners: Inside Large Language Modelszerotomastery.io

Category: Others
Duration 2 hours 59 minutes 17 seconds
Sidekiq in Practice

Sidekiq in PracticeNate Berkopec

Category: Others
Duration 1 hour 4 minutes 45 seconds
Product Design Portfolio Final Final book
Armin van Buuren Teaches Dance Music | MasterClass

Armin van Buuren Teaches Dance Music | MasterClassmasterclass

Category: Others
Duration 6 hours 50 minutes 39 seconds