Loading video player...
Master Search and RAG with this complete course by Isaac Flath. From keyword search to multimodal embeddings, learn how to build modern AI search systems hands-on. Learn Retrieval Augmented Generation - https://www.boot.dev/courses/learn-retrieval-augmented-generation Code "isaac" for 25% off. Go check out Isaac's channel! (https://www.youtube.com/@isaac-flath) CHAPTERS: 00:00 - Ch1 L1 - Retrieval Augmented Generation 01:29 - Ch1 L2 - What is search 05:41 - Ch1 L3 - Project Overview 07:52 - Ch1 L4 - Keyword Search 15:52 - Ch1 L5 - Text Processing 18:28 - Ch1 L6 - Punctuation 20:59 - Ch1 L7 - Tokenization 25:52 - Ch1 L8 - Stop words 33:35 - Ch1 L9 - Stemming 37:26 - Ch2 L1 - Inverted Index 45:52 - Ch2 L2 - Use the index 50:38 - Ch2 L3 - Boolean Search 52:05 - Ch2 L4 - Term Frequency 01:02:46 - Ch2 L5 - Inverse Document Frequency 01:08:06 - Ch2 L6 - TF-IDF 01:11:21 - Ch3 L1 - Keyword Search 01:18:58 - Ch3 L2 - Term Frequency Saturation 01:25:03 - Ch3 L3 - Document Length Normalization 01:36:00 - Ch3 L4 - BM25 Search 01:47:03 - Ch4 L1 - Semantic Search 01:50:23 - Ch4 L2 - Embeddings 01:52:04 - Ch4 L3 - Embedding Models 01:56:41 - Ch4 L4 - Model Selection 01:59:38 - Ch4 L5 - Vector Operations 02:02:31 - Ch4 L6 - Dimensions 02:04:22 - Ch4 L7 - Dot Product Similarity 02:06:18 - Ch4 L8 - Why Cosine Similarity? 02:10:54 - Ch4 L9 - Why Cosine Similarity 02:16:46 - Ch4 L11 - Document Embeddings 02:26:21 - Ch4 L12 - Query Embeddings 02:29:51 - Ch4 L13 - Same Model 02:32:17 - Ch4 L14 - Implementing Semantic Search 02:40:18 - Ch4 L15 - Locally-Sensitive Hashing 02:42:00 - Ch4 L16 - Vector Databases 02:44:14 - Ch5 L1 - Chunking 02:51:17 - Ch5 L2 - Chunk Overlap 02:57:17 - Ch5 Challenge - Semantic search basics 02:58:47 - Ch5 L3 - Semantic Chunking 03:06:03 - Ch5 L4 - Chunked Semantic Embeddings 03:19:49 - Ch5 L5 - Chunked Semantic Search 03:34:07 - Ch5 L6 - Chunked Edge Cases 03:37:47 - Ch5 L7 - ColBERT 03:41:03 - Ch5 L8 - Late Chunking 03:43:19 - Ch6 L1 - Keyword vs Semantic 03:44:50 - Ch6 L2 - Hybrid Search 03:48:53 - Ch6 L3 - Score Normalization 03:55:56 - Ch6 L4 - Weighted Combination 04:14:01 - Ch6 L5 - Reciprocal Rank Fusion 04:25:50 - Ch7 L1 - Large Language Models 04:27:29 - Ch7 L2 - Gemini API Setup 04:32:42 - Ch7 L3 - Spell Correction 04:40:59 - Ch7 L4 - Query Rewriting 04:43:35 - Ch7 L5 - Query Expansion 04:47:22 - Ch8 L1 - Re-Ranking 04:50:33 - Ch8 L2 - LLMs for Re-Ranking 05:05:45 - Ch8 L3 - LLM Batch Re-Ranking 05:18:41 - Ch8 L4 - Cross-Encoder Re-Ranking 05:25:38 - Ch9 L1 - Manual Evaluation 05:29:04 - Ch9 L2 - Golden Dataset 05:32:50 - Ch9 L3 - Precision Metrics 05:41:48 - Ch9 L4 - Recall Metrics 05:52:28 - Ch9 L5 - F1 Score 05:58:16 - Ch9 L6 - Error Analysis 06:12:46 - Ch9 L7 - LLM Evaluation 06:24:41 - Ch9 Challenge - Designing Chunking Strategy (Interview) 06:29:05 - Ch9 Challenge - Query -- Document Embeddings 06:30:14 - Ch10 L1 - Augmented Generation 06:40:20 - Ch10 L2 - LLM Summarization 06:47:34 - Ch10 L3 - Conflict Resolution in Summaries 06:49:33 - Ch10 L4 - Adding Citations 06:56:20 - Ch10 L5 - Question Answering 06:59:22 - Ch11 L1 - Recursive Rag 07:01:19 - Ch11 L2 - Agentic Search 07:03:12 - Ch12 L1 - Multimodal Search 07:11:19 - Ch12 L2 - Multimodal Embeddings 07:14:17 - Ch12 L3 - Image Embeddings 07:20:45 - Ch12 L4 - Multimodal Search Implementation Like & subscribe for the algo if you enjoyed the video!