Parseflow · Schema

Parseflow Indexed Document

Document record stored in the Parseflow keyword search index (POST /v2/index, GET /v2/search/documents/{id}).

Document ParsingPDFOCRText ExtractionDocument AISearchBYOKAsync JobsWebhooksREST

Properties

Name	Type	Description
document_id	string
filename	stringnull
indexed_at	string
chunk_count	integer
mode	string
extraction	objectnull
snippet	stringnull
metadata	objectnull

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://docs.parseflow.tech/schemas/indexed-document.json",
  "title": "Parseflow Indexed Document",
  "description": "Document record stored in the Parseflow keyword search index (POST /v2/index, GET /v2/search/documents/{id}).",
  "type": "object",
  "required": ["document_id", "indexed_at"],
  "properties": {
    "document_id": { "type": "string" },
    "filename": { "type": ["string", "null"] },
    "indexed_at": { "type": "string", "format": "date-time" },
    "chunk_count": { "type": "integer", "minimum": 0 },
    "mode": {
      "type": "string",
      "enum": ["basic", "deterministic", "byok_assisted"]
    },
    "extraction": {
      "type": ["object", "null"],
      "additionalProperties": true
    },
    "snippet": { "type": ["string", "null"] },
    "metadata": {
      "type": ["object", "null"],
      "additionalProperties": true
    }
  }
}