{
  "kind": "framework",
  "value": "vector-embeddings",
  "collectionKey": "slides:framework:vector-embeddings:all-document-kinds:all-producers:all-orientations",
  "filters": {
    "documentKinds": [],
    "sourceTypes": [],
    "orientations": []
  },
  "total": 1,
  "page": 1,
  "pageSize": 24,
  "pageCount": 1,
  "rows": [
    {
      "docId": "019dd923-5eff-723e-9be4-6cd7e97a57b9",
      "docSlug": "9be49d7769a68b67",
      "documentTitle": "2023 Investor Session Product Update",
      "authorId": "MongoDB",
      "authorName": "MongoDB",
      "documentKindSlug": "consulting-deck",
      "documentKindLabel": "Consulting deck",
      "sourceTypeSlug": "strategy_consulting",
      "sourceTypeLabel": "Strategy consulting",
      "presentationDate": null,
      "orientation": "landscape",
      "aspectRatio": 1.777,
      "pageNumber": 62,
      "slideType": "other",
      "function": "present_framework",
      "notes": "The slide illustrates the concept of vector embeddings in machine learning.",
      "imagePath": null,
      "matchCount": 1,
      "evidence": "Visual representation of semantic proximity in vector space",
      "slideHref": "/slides/019dd923-5eff-723e-9be4-6cd7e97a57b9/62",
      "deckHref": "/decks/019dd923-5eff-723e-9be4-6cd7e97a57b9",
      "deckAnchorHref": "/decks/019dd923-5eff-723e-9be4-6cd7e97a57b9#slide-62",
      "loopMatches": [],
      "arcBeatMatches": [],
      "imagePathAlt": null,
      "thumbSrc": null,
      "thumbSrcAlt": null,
      "locked": true
    }
  ]
}