llamaindex · Schema

ParseResult

The parsed output of a document, containing extracted content in various formats.

Properties

Name Type Description
text string Plain text representation of the parsed content.
markdown string Markdown-formatted representation of the parsed content.
json object Structured JSON representation of the parsed content.
pages array Per-page parsing results.
metadata object Metadata extracted from the document.
View JSON Schema on GitHub

JSON Schema

llamaindex-parseresult-schema.json Raw ↑ 
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/ParseResult",
  "title": "ParseResult",
  "type": "object",
  "description": "The parsed output of a document, containing extracted content in various formats.",
  "properties": {
    "text": {
      "type": "string",
      "description": "Plain text representation of the parsed content."
    },
    "markdown": {
      "type": "string",
      "description": "Markdown-formatted representation of the parsed content."
    },
    "json": {
      "type": "object",
      "additionalProperties": true,
      "description": "Structured JSON representation of the parsed content."
    },
    "pages": {
      "type": "array",
      "description": "Per-page parsing results.",
      "items": {
        "$ref": "#/components/schemas/ParsePage"
      }
    },
    "metadata": {
      "type": "object",
      "additionalProperties": true,
      "description": "Metadata extracted from the document."
    }
  }
}