RAG Essentials
Learn Retrieval Augmented Generation — the technique that lets AI answer questions using your own data
What is RAG and Why It Matters
Understand what Retrieval Augmented Generation is, how it solves the knowledge limitation of LLMs, and where it fits compared to fine-tuning.
Understanding Embeddings
Learn how text is converted into numerical vectors, why semantic similarity matters, and how to generate embeddings with popular models.
Vector Databases Explained
Explore what vector databases are, compare popular options like Pinecone, Weaviate, ChromaDB, and pgvector, and learn how to set up a basic vector store.
Building a RAG Pipeline
Build a complete RAG pipeline step by step — load documents, chunk them, generate embeddings, store in a vector database, and generate answers with context.
Chunking Strategies
Master the art of splitting documents for RAG — fixed-size, semantic, and recursive chunking strategies with best practices for every document type.
Evaluating RAG Quality
Learn how to measure and improve your RAG system with evaluation metrics for retrieval quality, generation faithfulness, and common failure modes.
RAG Essentials Cheat Sheet
Your complete quick reference for RAG — pipeline diagrams, embedding model comparisons, vector database selection, chunking decisions, and AI prompts.