AI Engineering Bootcamp: RAG (Retrieval Augmented Generation) for LLMs
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The limitations of many AI systems are related to their reliance on outdated data from their training samples.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:
- Basics of retrieval systems:
- How to prepare textual data for search
- Various search models (Boolean, vector, probabilistic)
- Indexing, queries, and data ranking
- Basics of generative models:
- Transformer architecture and attention mechanisms
- Data preparation and text model training
- Introduction to Retrieval-Augmented Generation:
- Combination of search and generation
- Key principles and application of RAG in real tasks
- Working with OpenAI API:
- API setup and effective use of prompts
- Configuration parameters and their impact on model behavior
- Implementation of RAG with OpenAI:
- Building fully functional RAG systems
- Integrating search and generation to solve complex tasks
- Working with unstructured data:
- Processing data from various formats: PDF, Word, PowerPoint, Excel, and images
- Extracting valuable information from texts and multimedia
- Multimodal RAG systems:
- Using textual and visual data to expand system capabilities
- Integrating different types of data into a single response
- 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
# | 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 | 06:36 |
8 | Tokenization Techniques | 07:00 |
9 | Preprocessing Steps | 09:36 |
10 | Types of Retrieval Systems | 07:07 |
11 | Vector Space Model (TF-IDF) | 09:45 |
12 | Implementing TF-IDF - Part 1 | 07:52 |
13 | Implementing TF-IDF - Part 2 | 04:16 |
14 | TF-IDF Function and Output Analysis | 04:58 |
15 | Boolean Retrieval Model | 06:04 |
16 | Preprocessing Steps - Part 2 | 06:56 |
17 | Setting a Directory | 06:05 |
18 | Boolean Retrieval Implementation | 08:43 |
19 | Probabilistic Retrieval Model | 07:15 |
20 | Probabilistic Retrieval Model Setup | 03:33 |
21 | Probabilistic Retrieval Model | 05:38 |
22 | How Google Search Works | 11:30 |
23 | Key Concepts: Indexing, Querying, and Ranking | 07:23 |
24 | What Did You Learn in This Section? | 02:32 |
25 | ReAct Prompt Engineering | 11:53 |
26 | Chain of Thought Prompt Engineering | 14:25 |
27 | Overview: Generative AI Fundamentals | 01:47 |
28 | Introduction to Text Generation | 04:10 |
29 | Understanding Transformers | 12:48 |
30 | Rock-Paper-Scissors, Dices and Strawberries | 08:25 |
31 | Getting a Hugging Face Key | 04:20 |
32 | Langchain and Hugging Face Setup | 13:09 |
33 | Basic Text Generation | 07:35 |
34 | Attention Mechanisms | 06:15 |
35 | Understanding Generation Model Parameters | 06:23 |
36 | System Message and Parameters | 15:00 |
37 | Text Generation with System Message | 06:15 |
38 | Text Generation with Parameters | 10:49 |
39 | OpenAI Playground - top P | 04:52 |
40 | What Did You Learn in This Section? | 01:40 |
41 | LLMs, Few-shot, Scaling and Factuality | 14:26 |
42 | Overview: RAG Fundamentals | 02:39 |
43 | Introduction to RAG Architecture | 05:18 |
44 | Hugging Face Setup | 06:30 |
45 | Tokenization and Embeddings for RAG | 09:03 |
46 | FAISS Index: Efficient Similarity Search | 04:16 |
47 | Building a Retrieval System | 04:31 |
48 | Developing a Generative Model | 07:42 |
49 | Implementing the RAG System | 07:53 |
50 | What Did You Learn in this Section? | 03:10 |
51 | LongRAG and LightRAG | 16:41 |
52 | Overview: Working with the OpenAI API | 03:48 |
53 | OpenAI API for Text | 08:48 |
54 | Setting Up OpenAI API Key | 05:50 |
55 | OpenAI API Setup | 04:32 |
56 | Generating Text with OpenAI API | 07:03 |
57 | OpenAI API Parameters | 10:21 |
58 | OpenAI API for Images | 08:15 |
59 | With Image URL | 04:55 |
60 | Converting Images to Base64 | 03:50 |
61 | Assess My Python Course Thumbnail | 04:49 |
62 | What Did You Learn in this Section? | 03:51 |
63 | Project Briefing: Customer Acquisition | 06:08 |
64 | OpenAI Setup | 05:40 |
65 | AI Agent System Prompt | 08:22 |
66 | Processing Images for GenAI | 05:25 |
67 | Extract Data with GenAI | 13:39 |
68 | Improving GenAI Extraction | 06:19 |
69 | GenAI with all Images | 06:56 |
70 | PDF to Images | 10:32 |
71 | Wrapping Up the OpenAI GenAI Project | 08:17 |
72 | Overview: RAG with OpenAI GPT Models | 04:35 |
73 | Case Study Briefing: Cooking Books | 04:58 |
74 | Converting PDF to Images | 09:16 |
75 | Reading a Single Image with GPT | 12:04 |
76 | Enhancing AI with Prompt Engineering | 09:11 |
77 | Reading All Images in a Dataset | 05:08 |
78 | Filtering Non-relevant Information | 06:04 |
79 | Understanding Embeddings in NLP | 06:51 |
80 | Generating Embeddings | 13:57 |
81 | Building FAISS Index and Metadata Integration | 06:28 |
82 | Implementing a Robust Retrieval System | 14:42 |
83 | Combining Outputs for Enhanced Results | 02:57 |
84 | Constructing a Generative Model | 11:43 |
85 | Complete RAG System Implementation | 06:42 |
86 | How to Improve RAG Systems Effectively? | 07:04 |
87 | Overview: Working With Unstructured Data | 03:37 |
88 | Introduction to Langchain Library | 07:27 |
89 | Excel Data: Best Practices for Data Handling | 06:42 |
90 | Python - Initial Setup for Data Processing | 05:48 |
91 | Loading Data and Implementing Chunking Strategies | 05:14 |
92 | Developing a Retrieval System for Unstructured Data | 06:11 |
93 | Building a Generation System for Dynamic Content | 09:13 |
94 | Building Retrieval and Generation Functions | 09:58 |
95 | Working with Word Documents | 04:55 |
96 | Setting Up Word Documents for RAG | 06:18 |
97 | Implementing RAG for Word Documents | 02:27 |
98 | Working with PowerPoint Presentations | 04:45 |
99 | PowerPoint Setup for RAG | 04:12 |
100 | RAG Implementation for PowerPoint | 03:10 |
101 | Working with EPUB Files | 04:59 |
102 | EPUB Setup for RAG | 04:48 |
103 | RAG Implementation for EPUB Files | 02:23 |
104 | Working with PDF Files | 04:22 |
105 | PDF Setup for RAG | 05:52 |
106 | RAG Implementation for PDF Files | 05:38 |
107 | What Did You Learn in This Section? | 03:57 |
108 | Exercise: Imposter Syndrome | 02:57 |
109 | Overview: Multimodal RAG | 03:39 |
110 | Introduction to Multimodal RAG | 05:59 |
111 | Setup and Video Processing | 05:24 |
112 | Extracting Audio from Video | 08:45 |
113 | Compressing Audio Files | 04:18 |
114 | Transcribing Audio with OpenAI Whisper | 10:08 |
115 | Whisper Model | 06:32 |
116 | Extracting Frames from Video | 05:50 |
117 | Introduction to Contrastive Learning | 05:15 |
118 | Understanding the CLIP Model | 05:23 |
119 | Tokenizing Text for Multimodal Tasks | 08:14 |
120 | Chunking and Embedding Text | 11:37 |
121 | Embedding Images for Multimodal Analysis | 08:37 |
122 | Understanding Cosine Similarity in Multimodal Contexts | 06:47 |
123 | Applying Contrastive Learning and Cosine Similarity | 10:27 |
124 | Visualizing Text and Image Embeddings | 11:12 |
125 | Query Embedding Techniques | 04:13 |
126 | Calculating Cosine Similarity for Query and Text | 11:48 |
127 | GenAI Model Setup for Multimodal Tasks | 04:56 |
128 | Building a GenAI Model | 07:12 |
129 | What Did You Learn in This Section? | 02:13 |
130 | Project Briefing: Starbucks Financial Data | 05:28 |
131 | Transcribing Audio with OpenAI Whisper | 11:23 |
132 | Embedding Transcription with CLIP | 07:36 |
133 | Converting PDF to Images | 05:58 |
134 | Embedding Images for Multimodal Analysis | 04:59 |
135 | Retrieval System | 17:14 |
136 | Preparing Context | 05:00 |
137 | Generative System | 12:47 |
138 | RAG with OpenAI File Search | 08:32 |
139 | Vector Stores in OpenAI | 05:53 |
140 | Setting a Vector Store in the OpenAI API | 05:47 |
141 | Responses Endpoint with File Search | 07:28 |
142 | RAG with GPT-4.1-mini | 07:00 |
143 | RAG with System Developper / Messages | 05:35 |
144 | Overview: Agentic RAG | 02:52 |
145 | AI Agents | 07:52 |
146 | Agentic RAG | 05:45 |
147 | Setup and Data Loading | 09:55 |
148 | State Management and Memory in Agentic Systems | 07:55 |
149 | AgentState Class | 04:30 |
150 | Greeting the Customer | 04:53 |
151 | AI Agent that Checks the Question | 10:48 |
152 | AI Agent that Assesses the Validity of the question | 07:23 |
153 | Retrieving the Documents | 05:47 |
154 | Testing the App | 07:14 |
155 | Generate Answers | 09:22 |
156 | AI Agent that Improves the Answer | 11:14 |
157 | Asking User For More Questions | 05:30 |
158 | Agentic RAG Recap - Key Learnings and Next Steps | 06:18 |
159 | Game Plan for Knowledge Graphs with LightRAG | 02:20 |
160 | Knowledge Graphs | 07:20 |
161 | Knowledge Graphs vs Embeddings | 08:50 |
162 | LightRAG Setup | 07:36 |
163 | What is LightRAG? | 04:41 |
164 | Setting the Working Directory | 02:29 |
165 | Data Prep | 04:49 |
166 | Naive RAG | 06:08 |
167 | Implementing LightRAG | 06:11 |
168 | Knowledge Graph Visualization | 08:21 |
169 | Local Knowledge Graph Visualization | 06:16 |
170 | Game Plan for RAGAS | 01:54 |
171 | Assessing RAG with RAGAS | 06:14 |
172 | RAGAS Setup | 03:51 |
173 | Embedding and Facebook AI Similarity Search (FAISS) | 09:52 |
174 | Python - RAG | 11:37 |
175 | Synthetic Data | 03:37 |
176 | Generating Synthetic Data | 04:59 |
177 | Python - Answering Synthetic Dataset | 06:29 |
178 | ROUGE (Recall-Oriented Understudy for Gisting Evaluation) Score | 05:33 |
179 | ROUGE | 13:50 |
180 | LLM-Based Assessment | 06:08 |
181 | Simple Criteria Score - Part 1 | 05:36 |
182 | Simple Criteria Score - Part 2 | 05:40 |
183 | Factual Correctness | 05:17 |
184 | Rubrics Score | 04:53 |
185 | Semantic Similarity | 04:47 |
186 | Factual Correctness | 05:17 |
187 | Context Precision | 03:13 |
188 | Semantic Similarity | 04:58 |
189 | Context Recall | 03:12 |
190 | Context Precision | 05:58 |
191 | Response Relevancy | 04:37 |
192 | Context Recall | 04:56 |
193 | Response Relevancy | 06:23 |
194 | Key Learnings and Outcomes: RAGAS | 03:18 |
195 | Thank You! | 01:18 |
Similar courses to AI Engineering Bootcamp: RAG (Retrieval Augmented Generation) for LLMs

Python for Financial Analysis and Algorithmic Tradingudemy

Replit AgentMckay Wrigley (takeoff)

Reprogram Your SubconsciousProdigies University

The World of Computer Networking. Your CCNA starts hereudemy

AI Coding with GitHub Copilotzerotomastery.io

Cisco CCNA 200-125 – The Complete Guide to Getting Certifiedudemy

Web Security & Bug Bounty Learn Penetration Testing in 2023zerotomastery.io

Ethical Hacking: Penetration Testingpluralsight

Build Side Projects With 500k+ Users: Coming Up With An IdeaAlex Chiou
