{
  "@context": "https://schema.org",
  "@type": "Dataset",
  "dateModified": "2026-06-02",
  "name": "Semantic Search Document Schema",
  "variableMeasured": [
    "docId",
    "sourceUrl",
    "title",
    "content",
    "contentHash",
    "embedding",
    "metadata",
    "lang",
    "jurisdiction",
    "serviceTag",
    "lastIndexed"
  ],
  "embeddingDim": 3072,
  "chunking": {
    "strategy": "recursive-paragraph",
    "targetChars": 900,
    "overlapChars": 150
  }
}