Advanced
RAG · LLM · Vector Search (AI Engineering)
The flagship professional course on building retrieval-augmented generation systems: from embeddings and vector search through the full RAG pipeline, advanced RAG techniques, and LangGraph.
#pro
68 lessons · 2h 58mCertificate
Featured
Curriculum
4 modules · 68 lessons · 2h 58m total
- Introduction to RAG - The Problem1m 47s
- The Problem That RAG Solves : Knowledge Staleness1m 23s
- The Problem That RAG Solves : Hallucination Risk1m 41s
- The Problem That RAG Solves : How RAG Reduces Hallucination Risk ?2m 11s
- The Problem That RAG Solves : Why Hallucination happens ?1m 57s
- The Problem That RAG Solves : Examples of Hallucinations1m 32s
- The Problem That RAG Solves : Domain Specific Gap2m 19s
- The Problem That RAG Solves : Why Finetuning Is Not Ideal ?1m 56s
- The Problem That RAG Solves : How RAG Solves Domain Specific Gaps ?2m 9s
- Indexing External Data1m 22s
- Document Collection — Step 1 of RAG2m 7s
- Document Chunking — Step 2 of RAG1m 58s
- Converting Text to Vectors — Step 3 of RAG4m 3s
- Sparse Representations — Traditional Text to Vectors3m 29s
- Converting Text to Vectors1m 30s
- Real Enterprise Example2m 29s
- Vector Indexing & Metadata1m 22s
- Vector DB lab - Try it
- Storing in a Vector Database — Step 4 of RAG2m 28s
- Scalable Semantic Search with Vector Indexing3m 1s
- Enterprise-Scale Vector Search & Indexing1m 6s
- The Three Core Components of Basic RAG3m 44s
- Embedding the User Query1m 48s
- Mathematical View of Retrieval2m 56s
- Enterprise RAG Retrieval — Pharmaceutical Example1m 52s
- ANN — Scalable Vector Search2m 36s
- Context Injection into LLM2m 6s
- Step 2: Retrieval — Semantic Search in High-Dimensional Vector Space3m 29s
- RAG Step 3 — Generation2m 8s
- Query-Time Step 2: Similarity Search in Vector Space3m 23s
- RAG Generation — Augmented Prompt & Template Design2m 30s
- Context Window Considerations2m 7s
- Grounded Generation Mechanism2m 7s
- Context Window & Grounded Generation3m 22s
- Context Window & Grounded Generation — Cinematic3m 43s
- Real Enterprise RAG Example — Pharmaceutical Query4m 18s
- How RAG Works — The Flow3m 56s
- Phase 1 — Data Preparation: Loading & Splitting3m 26s
- Managing Context, Retrieval & Augmentation in RAG3m 8s
- Augmentation (Prompting) in Retrieval-Augmented Generation7m 11s
- The RAG Chain Structure & Augmentation4m 54s
- The RAG Chain & Embedding Pipeline2m 59s
- Storing Data & RAG Chain Technical Details3m 0s
- Hybrid Rag lab - Try it
- Introduction to LangGraph15s
- LangGraph — From Basics to Real-World Workflow50s
- Input Dictionary & Runnable Passthrough5m 9s
- Prompt Component & Document Formatting5m 0s
- LLM Lab - Try it
- LLM & StrOutputParser in RAG5m 12s
- StrOutputParser & Query Translation6m 35s
- RAG Fusion & Decomposition4m 24s
- Step-Back Prompting & HyDE in RAG2m 31s
- Hyde RAG lab - Try it
- Routing in Retrieval-Augmented Generation (RAG)3m 56s
- Semantic Routing & Query Construction in Advanced RAG6m 28s
- Advanced Indexing Techniques in RAG4m 12s
- Active RAG & Flow Engineering2m 42s
- LangGraph & Adaptive RAG (C-RAG)3m 46s
- RAG Pipeline Workflow — Demonstration & Conclusion2m 28s
- Machine Learning Foundation for LLM Engineers1m 20s
- RAG Motivation: Bridging Public LLMs & Private Data1m 11s
- RAG Architecture3m 0s
- Intro to LangGraph5m 30s