{
  "dataset": "glossary",
  "record": {
    "id": "chunking",
    "term": "Chunking",
    "category": "knowledge-memory",
    "short_def": "Splitting a document into smaller passages so each can be embedded, indexed and retrieved independently in a RAG pipeline.",
    "long_def": "Chunking decides the unit of retrieval: documents are cut into passages (by size, by heading, or semantically) before embedding, so a query returns the few most relevant chunks rather than a whole document. Chunk size is a tradeoff — too large dilutes relevance, too small loses context.",
    "see_also": [
      "rag",
      "embeddings",
      "reranking"
    ],
    "etymology_origin": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation — 'chunking' is standard RAG-pipeline terminology"
    },
    "related_to": [
      "rag",
      "embeddings",
      "reranking",
      "vector-database"
    ],
    "contrast_with": "Unlike indexing a whole document as one unit, chunking retrieves passage-level pieces, so an agent gets the relevant paragraph instead of the entire file.",
    "example": "A 40-page manual chunked by section lets a query return just the two paragraphs that answer it, keeping the agent's context window focused.",
    "source": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation",
    "status": "active",
    "why_it_matters": "How you chunk determines what an agent retrieves; clean headings and self-contained sections (the same structure that makes content answer-first) chunk cleanly and lower Cost of Retrieval.",
    "sameAs": [
      "https://en.wikipedia.org/wiki/Retrieval-augmented_generation"
    ],
    "bridge_entity": "rag",
    "last_verified": "2026-07-06",
    "md_twin": "/glossary/chunking.md"
  }
}