Reducto · Schema

ClassifyConfig

Reducto ClassifyConfig schema

Document ParsingPDFOCRData ExtractionAIMachine LearningDocument IntelligenceStructured Data

Properties

Name	Type	Description
persist_results	boolean	If True, persist the results indefinitely. Defaults to False.
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
classification_schema	array	A list of classification categories and their matching criteria.
page_range	object	The page range to process (1-indexed). By default, the first 5 pages are used. If more than 25 pages are selected, only the first 25 (after sorting) are used. Only applies to PDFs; ignored for other d
document_metadata	string	Optional document-level metadata to include in classification prompts.

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-classifyconfig.json",
  "title": "ClassifyConfig",
  "description": "Reducto ClassifyConfig schema",
  "properties": {
    "persist_results": {
      "type": "boolean",
      "title": "Persist Results",
      "description": "If True, persist the results indefinitely. Defaults to False.",
      "default": false
    },
    "input": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "$ref": "#/components/schemas/UploadResponse"
        }
      ],
      "title": "Input",
      "description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following:\n            1. A publicly available URL\n            2. A presigned S3 URL\n            3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document\n            4. A jobid:// prefixed URL obtained from a previous /parse invocation\n            5. A list of URLs (for multi-document pipelines, V3 API only)\n\n            For edit pipelines, this should be a string containing the edit instructions "
    },
    "classification_schema": {
      "items": {
        "$ref": "#/components/schemas/ClassificationCategory"
      },
      "type": "array",
      "title": "Classification Schema",
      "description": "A list of classification categories and their matching criteria.",
      "default": []
    },
    "page_range": {
      "anyOf": [
        {
          "$ref": "#/components/schemas/PageRange"
        },
        {
          "items": {
            "$ref": "#/components/schemas/PageRange"
          },
          "type": "array"
        },
        {
          "items": {
            "type": "integer"
          },
          "type": "array"
        }
      ],
      "title": "Page Range",
      "description": "The page range to process (1-indexed). By default, the first 5 pages are used. If more than 25 pages are selected, only the first 25 (after sorting) are used. Only applies to PDFs; ignored for other document types.",
      "nullable": true
    },
    "document_metadata": {
      "type": "string",
      "nullable": true,
      "title": "Document Metadata",
      "description": "Optional document-level metadata to include in classification prompts."
    }
  },
  "type": "object",
  "required": [
    "input"
  ]
}