Skip to main content

Explore Problems

Certifications Quiz Pricing

⌘K

RAG & Retrieval Systems

Course Contents

From Words to Vectors (Depth)

Semantic Similarity: Cosine, Dot & Euclidean

Choosing & Fine-Tuning Embedding Models

Building a Semantic Search Engine from Scratch

Embeddings Beyond Search: Classification, Clustering & Dedup

Embedding Pitfalls (Domain Mismatch, Dimensionality)

Multilingual & Specialized Embeddings

Matryoshka & Quantized Embeddings (Cost/Scale)

Why Not Just Brute-Force Search? (ANN Intro)

Indexing Algorithms: HNSW & IVF

Tour of Vector DBs: pgvector, Pinecone, Weaviate, Chroma, Qdrant

Metadata & Filtered Search

Inserting, Updating & Scaling Your Index

Choosing the Right Vector Store

The RAG Pattern: Why Retrieval Beats Memorization

The End-to-End RAG Architecture

Ingestion: Loading & Parsing Documents

Retrieve → Augment → Generate (Build From Scratch)

Citing Sources & Grounding Answers

Common RAG Failure Modes

Why Chunking Makes or Breaks RAG

Fixed, Recursive & Sentence Chunking

Semantic & Sliding-Window Chunking

Parent-Child / Small-to-Big Retrieval

Contextual Retrieval & Metadata Enrichment (Anthropic, Late Chunking)

Multi-Vector & Summary Indexing

Hybrid Search: Dense + Sparse (BM25)

Reciprocal Rank Fusion (RRF)

Reranking & Late Interaction (Cross-Encoders, ColBERT)

Query Rewriting & HyDE

Multi-Query & Query Decomposition

Adaptive Retrieval Routing

A Production Retrieval Stack (Putting It Together)

Knowledge Graphs for Retrieval (Neo4j/Memgraph)

GraphRAG: Entities, Relationships & Global Reasoning

RAG over Tables, PDFs & Images (Multimodal)

Agentic RAG: Corrective RAG (C-RAG) & Self-RAG

Evaluating RAG (RAGAS: Faithfulness, Relevance, Context Precision/Recall)

RAG Design Decision Guide

Multi-Vector & Summary Indexing

Index one thing and return another — summaries and hypothetical questions as extra ways into a document, RAPTOR's recursive summary trees, and the costs and caveats of multi-vector indexing.

Loading...

Loading content...