Reducto · Schema

SyncParseConfig

Reducto SyncParseConfig schema

Document ParsingPDFOCRData ExtractionAIMachine LearningDocument IntelligenceStructured Data

Properties

Name	Type	Description
input	object	For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtaine
enhance	object
retrieval	object
formatting	object
spreadsheet	object
settings	object

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-syncparseconfig.json",
  "title": "SyncParseConfig",
  "description": "Reducto SyncParseConfig schema",
  "properties": {
    "input": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "$ref": "#/components/schemas/UploadResponse"
        }
      ],
      "title": "Input",
      "description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following:\n            1. A publicly available URL\n            2. A presigned S3 URL\n            3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document\n            4. A jobid:// prefixed URL obtained from a previous /parse invocation\n            5. A list of URLs (for multi-document pipelines, V3 API only)\n\n            For edit pipelines, this should be a string containing the edit instructions "
    },
    "enhance": {
      "$ref": "#/components/schemas/Enhance",
      "default": {
        "agentic": [],
        "summarize_figures": true,
        "intelligent_ordering": false
      }
    },
    "retrieval": {
      "$ref": "#/components/schemas/Retrieval",
      "default": {
        "chunking": {
          "chunk_mode": "disabled",
          "chunk_overlap": 0
        },
        "filter_blocks": [],
        "embedding_optimized": false
      }
    },
    "formatting": {
      "$ref": "#/components/schemas/Formatting",
      "default": {
        "add_page_markers": false,
        "table_output_format": "dynamic",
        "merge_tables": false,
        "include": []
      }
    },
    "spreadsheet": {
      "$ref": "#/components/schemas/Spreadsheet",
      "default": {
        "split_large_tables": {
          "enabled": true,
          "size": 50
        },
        "include": [],
        "clustering": "accurate",
        "exclude": []
      }
    },
    "settings": {
      "$ref": "#/components/schemas/Settings",
      "default": {
        "ocr_system": "standard",
        "extraction_mode": "hybrid",
        "force_url_result": false,
        "return_ocr_data": false,
        "return_images": [],
        "embed_pdf_metadata": false,
        "embed_pdf_metadata_dpi": 100,
        "persist_results": false,
        "hybrid_vpc": {}
      }
    }
  },
  "type": "object",
  "required": [
    "input"
  ]
}