RAG & Vectors
Chunking, Vector indexing, ANN search, cross-encoders, and 8 RAG architectures.
RAG Pipeline & Vector Indexing
intermediate~10hLearn document ingestion, chunking strategies, vector databases, and hybrid search pipelines.
Advanced RAG Architectures: HyDE, CAG, REFRAG
advanced~10hExplore Advanced RAG architectures: HyDE, Corrective RAG, Graph RAG, REFRAG, CAG, and Agentic RAG.
Text Classification and Clustering
intermediate~5hApplied text classification using zero-shot generative models, embedding+classifier pipelines, and fine-tuned encoders; plus unsupervised text clustering and topic modeling with K-Means, HDBSCAN, and BERTopic — all grounded in embedding space.
Embedding Model Fine-Tuning
advanced~6hBuilding and fine-tuning custom embedding models for domain-specific retrieval: contrastive learning with triplet loss, the SBERT architecture, MultipleNegativesRankingLoss for efficient training, hard negative mining, and Matryoshka Representation Learning for multi-size embeddings.
5 Chunking Strategies for RAG
intermediate~3hFixed-size, Semantic, Recursive, Document-structure-based, and LLM-based chunking — five distinct ways to split documents for RAG, each with different tradeoffs.
8 RAG Architectures: A Decision Map
intermediate~3hA taxonomy of 8 RAG architectures — Naive, Multimodal, HyDE, Corrective, Graph, Hybrid, Adaptive, and Agentic — with a decision framework for picking the right one.
Agentic RAG: Architecture & 12-Step Workflow
advanced~4hThe specific 12-step agentic RAG blueprint — query rewriting, a 'need more detail?' decision, source selection across vector DB/tools/internet, and a relevance-checking retry loop — that fixes traditional RAG's retrieve-once, reason-never limitations.
Prompting vs. RAG vs. Fine-tuning: A Decision Framework
intermediate~3hA 2-axis decision matrix (external knowledge needed vs. behavior adaptation needed) for choosing between prompt engineering, RAG, fine-tuning, or a hybrid — plus a deeper 3-way comparison of full fine-tuning, LoRA, and RAG.