📚

RAG & Vectors

Chunking, Vector indexing, ANN search, cross-encoders, and 8 RAG architectures.

1

RAG Pipeline & Vector Indexing

intermediate~10h

Learn document ingestion, chunking strategies, vector databases, and hybrid search pipelines.

2

Advanced RAG Architectures: HyDE, CAG, REFRAG

advanced~10h

Explore Advanced RAG architectures: HyDE, Corrective RAG, Graph RAG, REFRAG, CAG, and Agentic RAG.

3

Text Classification and Clustering

intermediate~5h

Applied 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.

4

Embedding Model Fine-Tuning

advanced~6h

Building 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

5 Chunking Strategies for RAG

intermediate~3h

Fixed-size, Semantic, Recursive, Document-structure-based, and LLM-based chunking — five distinct ways to split documents for RAG, each with different tradeoffs.

6

8 RAG Architectures: A Decision Map

intermediate~3h

A taxonomy of 8 RAG architectures — Naive, Multimodal, HyDE, Corrective, Graph, Hybrid, Adaptive, and Agentic — with a decision framework for picking the right one.

7

Agentic RAG: Architecture & 12-Step Workflow

advanced~4h

The 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.

8

Prompting vs. RAG vs. Fine-tuning: A Decision Framework

intermediate~3h

A 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.