Retrieval & Agents
Chunking
Splitting documents into smaller passages before indexing them, a foundational step that makes or breaks a RAG system.
Chunking breaks long documents into bite-sized passages so each can be embedded and retrieved on its own. The size and boundaries matter a lot: chunks too large dilute relevance and waste context, too small lose the surrounding meaning. Good chunking, often along natural boundaries like paragraphs or sections, is one of the highest-leverage tuning decisions in a retrieval system.
Related terms
Retrieval-Augmented Generation
A technique that looks up relevant documents and feeds them to a model so its answers are grounded in real sources.
Embedding
A way of turning words, images, or other data into lists of numbers that capture their meaning, so a computer can compare them.
Vector Database
A database built to store embeddings and quickly find the items most similar in meaning to a query.
Context Window
The maximum amount of text, measured in tokens, that a model can consider at once.