Agentic RAG

Retrieval-Augmented Generation from first principles

Semantic, recursive, agentic chunking — choosing the right approach

Choosing models and storage for your use case

Hybrid search, reranking, query expansion

Self-RAG, corrective RAG, adaptive retrieval

Multi-step retrieval with query decomposition

Faithfulness, relevance, and answer quality metrics

Scaling, caching, and real-time indexing

Graph RAG, multimodal RAG, conversational RAG

The most common RAG mistakes and how to fix them

Naive vs. production RAG patterns side by side

Production-ready guidelines for every RAG stage

Papers, docs, and guides

Gemini 2.5 Pro 1M context changes the calculus for document Q&A

Voyage AI, Cohere v4, nomic-embed — choosing the right embedding model