What is Chunking?
Splitting content into retrievable passages for embeddings and RAG. Clear headings, one idea per section, and definitions up front make chunks that rank and quote cleanly.
Related terms
Chunk Retrieval
The step in RAG where a system pulls the most relevant passages (chunks) from its index to feed the model. Pages with self-contained, fact-dense sections produce chunks that survive this selection.
Vector Embedding
A numeric representation of text meaning used to match queries to passages by semantic similarity rather than exact keywords. Embeddings power chunk retrieval in AI search.
Passage Embedding
The vector representation of a single section used in passage-level retrieval. One idea per section with the answer up front produces embeddings that match focused queries.
Answer Engine Optimization (AEO)
Answer Engine Optimization is the practice of structuring pages so answer engines and AI assistants can extract, trust, and quote them: a direct definition up top, scannable steps, quotable facts, and FAQ or Article schema behind them.
Generative Engine Optimization (GEO)
Generative Engine Optimization improves how often a brand or page is cited inside AI-generated answers. It combines classic SEO (crawlability, relevance) with quotability: clear facts, named entities, sources, and machine-readable structure.
AI Overviews
Google’s AI-generated summaries at the top of some results pages. They synthesize multiple sources and link to them, which can reduce clicks to publishers even when a page ranks well organically.