Skip to main content

Documentation Index

Fetch the complete documentation index at: https://developers.lighton.ai/llms.txt

Use this file to discover all available pages before exploring further.

Parse converts a document to structured Markdown without storing or indexing it. The call is synchronous — send a file, get Markdown back immediately. Use Parse when you want the text content of a document for your own purposes: feeding it to an LLM, storing it in your database, displaying it in a UI, or pre-processing it before ingestion. Nothing is saved on LightOn’s side.
If you want the document to be searchable, use Files instead — it ingests and indexes the document permanently. The full schema for POST /api/v3/parse is in the API reference.

​
Parse a document

import requests

response = requests.post(
    "https://api.lighton.ai/api/v3/parse",
    headers={"Authorization": "Bearer $CONSOLE_API_KEY"},
    files={"file": open("report.pdf", "rb")},
)

markdown = response.json()["result"]["content"]
print(markdown[:200])
# → # Q4 Financial Report\n\n## Executive Summary\n\nRevenue grew 18%…
file (multipart) and document (JSON URL) are mutually exclusive — pass one or the other.

​
What comes back

The response includes the Markdown content along with metadata about the original document: 
{
  "id": "parse_0196e4b2a3c14d5e8f7a9b2c1d0e3f4a",
  "status": "completed",
  "created_at": "2026-03-31T10:00:00+00:00",
  "completed_at": "2026-03-31T10:00:03+00:00",
  "processing_time_ms": 2840,
  "document": {
    "filename": "report.pdf",
    "page_count": 3,
    "file_size_bytes": 245120,
    "mime_type": "application/pdf"
  },
  "result": {
    "content": "# Invoice\n\nInvoice Number: INV-2026-001\nDate: March 15, 2026\n…"
  },
  "usage": {
    "pages_processed": 3
  }
}
The result.content field is the full document as Markdown. Headings, lists, tables, and code blocks are preserved where the source document supports them.

​
Supported formats and limits

Formats: .pdf, .png, .jpg, .jpeg, .pptx, .ppt, .odp, .docx, .odt, .doc, .html Sync limits: 20 MB per file · 15 pages per request For longer documents, split into chunks before calling Parse, or ingest the full document with Files and use Search to retrieve relevant sections.

​
Common errors

StatusCause
400Missing document, unsupported format, or page limit exceeded
401Missing or invalid API key
413File exceeds the 20 MB size limit
429Rate limit exceeded
503Parsing backend is overloaded — retry later