Reducto · Schema

ParseChunk

Reducto ParseChunk schema

Document ParsingPDFOCRData ExtractionAIMachine LearningDocument IntelligenceStructured Data

Properties

Name	Type	Description
content	string	The content of the chunk extracted from the document.
embed	string	Chunk content optimized for embedding and retrieval.
enriched	string	The enriched content of the chunk extracted from the document.
enrichment_success	boolean	Whether the enrichment was successful.
blocks	array

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/reducto/refs/heads/main/json-schema/reducto-parsechunk.json",
  "title": "ParseChunk",
  "description": "Reducto ParseChunk schema",
  "properties": {
    "content": {
      "type": "string",
      "title": "Content",
      "description": "The content of the chunk extracted from the document."
    },
    "embed": {
      "type": "string",
      "title": "Embed",
      "description": "Chunk content optimized for embedding and retrieval."
    },
    "enriched": {
      "type": "string",
      "nullable": true,
      "title": "Enriched",
      "description": "The enriched content of the chunk extracted from the document."
    },
    "enrichment_success": {
      "type": "boolean",
      "title": "Enrichment Success",
      "description": "Whether the enrichment was successful.",
      "default": false
    },
    "blocks": {
      "items": {
        "$ref": "#/components/schemas/ParseBlock"
      },
      "type": "array",
      "title": "Blocks"
    }
  },
  "type": "object",
  "required": [
    "content",
    "embed",
    "enriched",
    "blocks"
  ]
}