RAG

RAG retrieves relevant external information and gives it to a language model as context before it answers.

RAG has two phases — offline ingestion (chunk, embed, store) and per-query answering (retrieve, rerank, generate) — connected by a vector store.

Chunking splits documents into smaller passages so they can be embedded and retrieved precisely; chunk size and overlap are key tuning knobs for RAG quality.

Query transformation rewrites, expands, or reframes the user's question before retrieval so the search finds better chunks.

A reranker re-scores the shortlist of retrieved chunks by reading each query-document pair closely, pushing the most relevant results to the top.

Contextual retrieval prepends a short context blurb to each chunk before embedding, so ambiguous passages become self-explanatory and retrieve accurately.

Agentic RAG turns the one-shot pipeline into a self-correcting loop that judges its own retrieval and answers, plus patterns like Graph RAG and multi-hop.

RAG evaluation measures retrieval quality (context precision/recall) and generation quality (faithfulness, answer relevance) separately to find and fix failures.

RAG adds knowledge at answer time, fine-tuning bakes behavior into weights, and long context pastes everything into the prompt — each fits different problems.