llamaindex · Schema

ParsePage

Parsed content for a single page of a document.

Properties

Name Type Description
page_number integer 1-based page number.
text string Plain text content of the page.
markdown string Markdown-formatted content of the page.
View JSON Schema on GitHub

JSON Schema

llamaindex-parsepage-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/ParsePage",
  "title": "ParsePage",
  "type": "object",
  "description": "Parsed content for a single page of a document.",
  "properties": {
    "page_number": {
      "type": "integer",
      "minimum": 1,
      "description": "1-based page number."
    },
    "text": {
      "type": "string",
      "description": "Plain text content of the page."
    },
    "markdown": {
      "type": "string",
      "description": "Markdown-formatted content of the page."
    }
  }
}