Upstage Document Parse

Convert documents into structured HTML/Markdown. Recognizes layout elements such as tables, images, equations, and charts with bounding box coordinates.

Quick Start

import os
import requests

with open("report.pdf", "rb") as f:
    response = requests.post(
        "https://api.upstage.ai/v1/document-digitization",
        headers={"Authorization": f"Bearer {os.environ['UPSTAGE_API_KEY']}"},
        files={"document": f},
        data={"model": "document-parse", "output_formats": "['markdown']"}
    )
print(response.json()["content"]["markdown"])

API Key: Always use os.environ["UPSTAGE_API_KEY"]. Get your key at console.upstage.ai.

Supported Formats

JPEG, PNG, BMP, PDF (up to 1000 pages with async), TIFF, HEIC, DOCX, PPTX, XLSX, HWP, HWPX

Sync vs Async

Decision rule:

• ≤ 100 pages and expected to finish within 5 min → sync.
• 100 pages, scanned/complex content, or batch jobs → async.

For async submit/poll workflow, see references/async-workflow.md.

Key Parameters (Sync)

For full parameter reference and curl variations (enhanced mode, force OCR, base64 table images, LangChain integration), see references/sync-options.md.

Response Structure

{
  "api": "2.0",
  "model": "document-parse-251217",
  "content": {
    "html": "<h1>...</h1>",
    "markdown": "# ...",
    "text": "..."
  },
  "elements": [
    {
      "id": 0,
      "category": "heading1",
      "content": { "html": "...", "markdown": "...", "text": "..." },
      "page": 1,
      "coordinates": [{"x": 0.06, "y": 0.05}, ...]
    }
  ],
  "usage": { "pages": 1 }
}

Element Categories

paragraph, heading1, heading2, heading3, list, table, figure, chart, equation, caption, header, footer, index, footnote

Output Files

• Default: write to /.parsed. where matches output_formats (md or html). Example: /tmp/report.parsed.md. Use tempfile.gettempdir() for cross-platform code.
• Override: if the user specifies an output path, use it.
• Always print the resolved absolute path in your response so the user can locate the file.

Tips

• Use mode=enhanced for complex tables, charts, images
• Use mode=auto to let API decide per page
• Use async API for documents > 100 pages, > 50 MB, or when sync would exceed the 5-min timeout (async caps at 1000 pages)
• Use ocr=force for scanned PDFs or images
• merge_multipage_tables=true combines split tables (max 20 pages with enhanced mode)
• Standard documents process in ~3 seconds; sync API timeout is 5 minutes

Detailed References