Этот материал находится в платной подписке. Оформи премиум подписку и смотри или слушай AI Engineering Bootcamp: RAG (Retrieval Augmented Generation) for LLMs, а также все другие курсы, прямо сейчас!
Премиум
  • Урок 1. 00:08:12
    Course Outline
  • Урок 2. 00:06:05
    Meet Rubber Ducky! Your AI Course Assistant using RAG
  • Урок 3. 00:04:05
    Overview: Fundamentals of Retrieval Systems
  • Урок 4. 00:05:38
    Overview of Information Retrieval
  • Урок 5. 00:07:21
    What is Tokenization?
  • Урок 6. 00:06:13
    OpenAI Tokenizer
  • Урок 7. 00:06:36
    Libraries and Data Handling for RAG
  • Урок 8. 00:07:00
    Tokenization Techniques
  • Урок 9. 00:09:36
    Preprocessing Steps
  • Урок 10. 00:07:07
    Types of Retrieval Systems
  • Урок 11. 00:09:45
    Vector Space Model (TF-IDF)
  • Урок 12. 00:07:52
    Implementing TF-IDF - Part 1
  • Урок 13. 00:04:16
    Implementing TF-IDF - Part 2
  • Урок 14. 00:04:58
    TF-IDF Function and Output Analysis
  • Урок 15. 00:06:04
    Boolean Retrieval Model
  • Урок 16. 00:06:56
    Preprocessing Steps - Part 2
  • Урок 17. 00:06:05
    Setting a Directory
  • Урок 18. 00:08:43
    Boolean Retrieval Implementation
  • Урок 19. 00:07:15
    Probabilistic Retrieval Model
  • Урок 20. 00:03:33
    Probabilistic Retrieval Model Setup
  • Урок 21. 00:05:38
    Probabilistic Retrieval Model
  • Урок 22. 00:11:30
    How Google Search Works
  • Урок 23. 00:07:23
    Key Concepts: Indexing, Querying, and Ranking
  • Урок 24. 00:02:32
    What Did You Learn in This Section?
  • Урок 25. 00:11:53
    ReAct Prompt Engineering
  • Урок 26. 00:14:25
    Chain of Thought Prompt Engineering
  • Урок 27. 00:01:47
    Overview: Generative AI Fundamentals
  • Урок 28. 00:04:10
    Introduction to Text Generation
  • Урок 29. 00:12:48
    Understanding Transformers
  • Урок 30. 00:08:25
    Rock-Paper-Scissors, Dices and Strawberries
  • Урок 31. 00:04:20
    Getting a Hugging Face Key
  • Урок 32. 00:13:09
    Langchain and Hugging Face Setup
  • Урок 33. 00:07:35
    Basic Text Generation
  • Урок 34. 00:06:15
    Attention Mechanisms
  • Урок 35. 00:06:23
    Understanding Generation Model Parameters
  • Урок 36. 00:15:00
    System Message and Parameters
  • Урок 37. 00:06:15
    Text Generation with System Message
  • Урок 38. 00:10:49
    Text Generation with Parameters
  • Урок 39. 00:04:52
    OpenAI Playground - top P
  • Урок 40. 00:01:40
    What Did You Learn in This Section?
  • Урок 41. 00:14:26
    LLMs, Few-shot, Scaling and Factuality
  • Урок 42. 00:02:39
    Overview: RAG Fundamentals
  • Урок 43. 00:05:18
    Introduction to RAG Architecture
  • Урок 44. 00:06:30
    Hugging Face Setup
  • Урок 45. 00:09:03
    Tokenization and Embeddings for RAG
  • Урок 46. 00:04:16
    FAISS Index: Efficient Similarity Search
  • Урок 47. 00:04:31
    Building a Retrieval System
  • Урок 48. 00:07:42
    Developing a Generative Model
  • Урок 49. 00:07:53
    Implementing the RAG System
  • Урок 50. 00:03:10
    What Did You Learn in this Section?
  • Урок 51. 00:16:41
    LongRAG and LightRAG
  • Урок 52. 00:03:48
    Overview: Working with the OpenAI API
  • Урок 53. 00:08:48
    OpenAI API for Text
  • Урок 54. 00:05:50
    Setting Up OpenAI API Key
  • Урок 55. 00:04:32
    OpenAI API Setup
  • Урок 56. 00:07:03
    Generating Text with OpenAI API
  • Урок 57. 00:10:21
    OpenAI API Parameters
  • Урок 58. 00:08:15
    OpenAI API for Images
  • Урок 59. 00:04:55
    With Image URL
  • Урок 60. 00:03:50
    Converting Images to Base64
  • Урок 61. 00:04:49
    Assess My Python Course Thumbnail
  • Урок 62. 00:03:51
    What Did You Learn in this Section?
  • Урок 63. 00:06:08
    Project Briefing: Customer Acquisition
  • Урок 64. 00:05:40
    OpenAI Setup
  • Урок 65. 00:08:22
    AI Agent System Prompt
  • Урок 66. 00:05:25
    Processing Images for GenAI
  • Урок 67. 00:13:39
    Extract Data with GenAI
  • Урок 68. 00:06:19
    Improving GenAI Extraction
  • Урок 69. 00:06:56
    GenAI with all Images
  • Урок 70. 00:10:32
    PDF to Images
  • Урок 71. 00:08:17
    Wrapping Up the OpenAI GenAI Project
  • Урок 72. 00:04:35
    Overview: RAG with OpenAI GPT Models
  • Урок 73. 00:04:58
    Case Study Briefing: Cooking Books
  • Урок 74. 00:09:16
    Converting PDF to Images
  • Урок 75. 00:12:04
    Reading a Single Image with GPT
  • Урок 76. 00:09:11
    Enhancing AI with Prompt Engineering
  • Урок 77. 00:05:08
    Reading All Images in a Dataset
  • Урок 78. 00:06:04
    Filtering Non-relevant Information
  • Урок 79. 00:06:51
    Understanding Embeddings in NLP
  • Урок 80. 00:13:57
    Generating Embeddings
  • Урок 81. 00:06:28
    Building FAISS Index and Metadata Integration
  • Урок 82. 00:14:42
    Implementing a Robust Retrieval System
  • Урок 83. 00:02:57
    Combining Outputs for Enhanced Results
  • Урок 84. 00:11:43
    Constructing a Generative Model
  • Урок 85. 00:06:42
    Complete RAG System Implementation
  • Урок 86. 00:07:04
    How to Improve RAG Systems Effectively?
  • Урок 87. 00:03:37
    Overview: Working With Unstructured Data
  • Урок 88. 00:07:27
    Introduction to Langchain Library
  • Урок 89. 00:06:42
    Excel Data: Best Practices for Data Handling
  • Урок 90. 00:05:48
    Python - Initial Setup for Data Processing
  • Урок 91. 00:05:14
    Loading Data and Implementing Chunking Strategies
  • Урок 92. 00:06:11
    Developing a Retrieval System for Unstructured Data
  • Урок 93. 00:09:13
    Building a Generation System for Dynamic Content
  • Урок 94. 00:09:58
    Building Retrieval and Generation Functions
  • Урок 95. 00:04:55
    Working with Word Documents
  • Урок 96. 00:06:18
    Setting Up Word Documents for RAG
  • Урок 97. 00:02:27
    Implementing RAG for Word Documents
  • Урок 98. 00:04:45
    Working with PowerPoint Presentations
  • Урок 99. 00:04:12
    PowerPoint Setup for RAG
  • Урок 100. 00:03:10
    RAG Implementation for PowerPoint
  • Урок 101. 00:04:59
    Working with EPUB Files
  • Урок 102. 00:04:48
    EPUB Setup for RAG
  • Урок 103. 00:02:23
    RAG Implementation for EPUB Files
  • Урок 104. 00:04:22
    Working with PDF Files
  • Урок 105. 00:05:52
    PDF Setup for RAG
  • Урок 106. 00:05:38
    RAG Implementation for PDF Files
  • Урок 107. 00:03:57
    What Did You Learn in This Section?
  • Урок 108. 00:02:57
    Exercise: Imposter Syndrome
  • Урок 109. 00:03:39
    Overview: Multimodal RAG
  • Урок 110. 00:05:59
    Introduction to Multimodal RAG
  • Урок 111. 00:05:24
    Setup and Video Processing
  • Урок 112. 00:08:45
    Extracting Audio from Video
  • Урок 113. 00:04:18
    Compressing Audio Files
  • Урок 114. 00:10:08
    Transcribing Audio with OpenAI Whisper
  • Урок 115. 00:06:32
    Whisper Model
  • Урок 116. 00:05:50
    Extracting Frames from Video
  • Урок 117. 00:05:15
    Introduction to Contrastive Learning
  • Урок 118. 00:05:23
    Understanding the CLIP Model
  • Урок 119. 00:08:14
    Tokenizing Text for Multimodal Tasks
  • Урок 120. 00:11:37
    Chunking and Embedding Text
  • Урок 121. 00:08:37
    Embedding Images for Multimodal Analysis
  • Урок 122. 00:06:47
    Understanding Cosine Similarity in Multimodal Contexts
  • Урок 123. 00:10:27
    Applying Contrastive Learning and Cosine Similarity
  • Урок 124. 00:11:12
    Visualizing Text and Image Embeddings
  • Урок 125. 00:04:13
    Query Embedding Techniques
  • Урок 126. 00:11:48
    Calculating Cosine Similarity for Query and Text
  • Урок 127. 00:04:56
    GenAI Model Setup for Multimodal Tasks
  • Урок 128. 00:07:12
    Building a GenAI Model
  • Урок 129. 00:02:13
    What Did You Learn in This Section?
  • Урок 130. 00:05:28
    Project Briefing: Starbucks Financial Data
  • Урок 131. 00:11:23
    Transcribing Audio with OpenAI Whisper
  • Урок 132. 00:07:36
    Embedding Transcription with CLIP
  • Урок 133. 00:05:58
    Converting PDF to Images
  • Урок 134. 00:04:59
    Embedding Images for Multimodal Analysis
  • Урок 135. 00:17:14
    Retrieval System
  • Урок 136. 00:05:00
    Preparing Context
  • Урок 137. 00:12:47
    Generative System
  • Урок 138. 00:08:32
    RAG with OpenAI File Search
  • Урок 139. 00:05:53
    Vector Stores in OpenAI
  • Урок 140. 00:05:47
    Setting a Vector Store in the OpenAI API
  • Урок 141. 00:07:28
    Responses Endpoint with File Search
  • Урок 142. 00:07:00
    RAG with GPT-4.1-mini
  • Урок 143. 00:05:35
    RAG with System Developper / Messages
  • Урок 144. 00:02:52
    Overview: Agentic RAG
  • Урок 145. 00:07:52
    AI Agents
  • Урок 146. 00:05:45
    Agentic RAG
  • Урок 147. 00:09:55
    Setup and Data Loading
  • Урок 148. 00:07:55
    State Management and Memory in Agentic Systems
  • Урок 149. 00:04:30
    AgentState Class
  • Урок 150. 00:04:53
    Greeting the Customer
  • Урок 151. 00:10:48
    AI Agent that Checks the Question
  • Урок 152. 00:07:23
    AI Agent that Assesses the Validity of the question
  • Урок 153. 00:05:47
    Retrieving the Documents
  • Урок 154. 00:07:14
    Testing the App
  • Урок 155. 00:09:22
    Generate Answers
  • Урок 156. 00:11:14
    AI Agent that Improves the Answer
  • Урок 157. 00:05:30
    Asking User For More Questions
  • Урок 158. 00:06:18
    Agentic RAG Recap - Key Learnings and Next Steps
  • Урок 159. 00:02:20
    Game Plan for Knowledge Graphs with LightRAG
  • Урок 160. 00:07:20
    Knowledge Graphs
  • Урок 161. 00:08:50
    Knowledge Graphs vs Embeddings
  • Урок 162. 00:07:36
    LightRAG Setup
  • Урок 163. 00:04:41
    What is LightRAG?
  • Урок 164. 00:02:29
    Setting the Working Directory
  • Урок 165. 00:04:49
    Data Prep
  • Урок 166. 00:06:08
    Naive RAG
  • Урок 167. 00:06:11
    Implementing LightRAG
  • Урок 168. 00:08:21
    Knowledge Graph Visualization
  • Урок 169. 00:06:16
    Local Knowledge Graph Visualization
  • Урок 170. 00:01:54
    Game Plan for RAGAS
  • Урок 171. 00:06:14
    Assessing RAG with RAGAS
  • Урок 172. 00:03:51
    RAGAS Setup
  • Урок 173. 00:09:52
    Embedding and Facebook AI Similarity Search (FAISS)
  • Урок 174. 00:11:37
    Python - RAG
  • Урок 175. 00:03:37
    Synthetic Data
  • Урок 176. 00:04:59
    Generating Synthetic Data
  • Урок 177. 00:06:29
    Python - Answering Synthetic Dataset
  • Урок 178. 00:05:33
    ROUGE (Recall-Oriented Understudy for Gisting Evaluation) Score
  • Урок 179. 00:13:50
    ROUGE
  • Урок 180. 00:06:08
    LLM-Based Assessment
  • Урок 181. 00:05:36
    Simple Criteria Score - Part 1
  • Урок 182. 00:05:40
    Simple Criteria Score - Part 2
  • Урок 183. 00:05:17
    Factual Correctness
  • Урок 184. 00:04:53
    Rubrics Score
  • Урок 185. 00:04:47
    Semantic Similarity
  • Урок 186. 00:05:17
    Factual Correctness
  • Урок 187. 00:03:13
    Context Precision
  • Урок 188. 00:04:58
    Semantic Similarity
  • Урок 189. 00:03:12
    Context Recall
  • Урок 190. 00:05:58
    Context Precision
  • Урок 191. 00:04:37
    Response Relevancy
  • Урок 192. 00:04:56
    Context Recall
  • Урок 193. 00:06:23
    Response Relevancy
  • Урок 194. 00:03:18
    Key Learnings and Outcomes: RAGAS
  • Урок 195. 00:01:18
    Thank You!