Dust Document

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/dust-tt/main/json-schema/dust-document-schema.json",
  "title": "Dust Document",
  "description": "A document upserted into a Dust data source, indexed for semantic search and agent retrieval.",
  "type": "object",
  "properties": {
    "data_source_id": {
      "type": "string",
      "example": "3b7d9f1e5a"
    },
    "created": {
      "type": "number",
      "example": 1625097600
    },
    "document_id": {
      "type": "string",
      "example": "2c4a6e8d0f"
    },
    "title": {
      "type": "string",
      "description": "Title of the document",
      "example": "Customer Support FAQ"
    },
    "mime_type": {
      "type": "string",
      "description": "MIME type of the table",
      "example": "text/md"
    },
    "timestamp": {
      "type": "number",
      "example": 1625097600
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "example": [
        "customer_support",
        "faq"
      ]
    },
    "parent_id": {
      "type": "string",
      "description": "ID of the document parent",
      "items": {
        "type": "string"
      },
      "example": "1234f4567c"
    },
    "parents": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "example": [
        "7b9d1f3e5a",
        "2c4a6e8d0f"
      ]
    },
    "source_url": {
      "type": "string",
      "nullable": true,
      "example": "https://example.com/support/article1"
    },
    "hash": {
      "type": "string",
      "example": "a1b2c3d4e5"
    },
    "text_size": {
      "type": "number",
      "example": 1024
    },
    "chunk_count": {
      "type": "number",
      "example": 5
    },
    "chunks": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "example": [
        {
          "chunk_id": "9f1d3b5a7c",
          "text": "This is the first chunk of the document.",
          "embedding": [
            0.1,
            0.2,
            0.3,
            0.4
          ]
        },
        {
          "chunk_id": "4a2c6e8b0d",
          "text": "This is the second chunk of the document.",
          "embedding": [
            0.5,
            0.6,
            0.7,
            0.8
          ]
        }
      ]
    },
    "text": {
      "type": "string",
      "example": "This is the full text content of the document. It contains multiple paragraphs and covers various topics related to customer support."
    },
    "token_count": {
      "type": "number",
      "nullable": true,
      "example": 150
    }
  }
}