PDF to Markdown

export MUNITO_API_KEY="munitoai_..."

curl https://api.munito.ai/inference/v1/ocr \
  -H "Authorization: Bearer $MUNITO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lightonai/lightonocr-2-1b",
    "document": {"type": "url", "url": "https://arxiv.org/pdf/1706.03762"},
    "pages": [0, 1]
  }'

{
  "request_id": "01a165c4-00db-7c89-8558-034e9b948463",
  "model": "lightonai/lightonocr-2-1b",
  "service_tier": "standard",
  "pages": [
    {
      "index": 0,
      "markdown": "# Attention Is All You Need\n\n...",
      "header": null,
      "footer": null,
      "page_number": null,
      "aside": null,
      "images": [],
      "tables": [],
      "dimensions": {
        "width": 1190,
        "height": 1540,
        "dpi": 140
      },
      "confidence_scores": null,
      "error": null,
      "error_code": null,
      "price_usd": 0.004
    }
  ],
  "usage": {
    "pages_processed": 2,
    "pages_failed": 0,
    "doc_size_bytes": 0,
    "cost_usd": 0.008,
    "price_per_page_usd": 0.004,
    "inference_region": "eu"
  }
}

# pip install requests
import base64
import os
import sys
import time

import requests

HOST = "https://api.munito.ai"
HEADERS = {"Authorization": f"Bearer {os.environ['MUNITO_API_KEY']}"}


def submit(path: str) -> str:
    """Send the PDF as base64 and return the location to poll."""
    with open(path, "rb") as f:
        data = base64.b64encode(f.read()).decode()
    response = requests.post(
        f"{HOST}/inference/v1/ocr",
        headers={**HEADERS, "Prefer": "respond-async"},
        json={
            "model": "munito/ocr-auto",
            "document": {"type": "base64", "data": data, "filename": os.path.basename(path)},
        },
        timeout=120,
    )
    response.raise_for_status()
    return response.json()["location"]


def wait(location: str) -> dict:
    """Poll the request until its status is final."""
    while True:
        response = requests.get(HOST + location, headers=HEADERS, timeout=60)
        if response.status_code == 503:
            time.sleep(int(response.headers.get("Retry-After", "2")))
            continue
        response.raise_for_status()
        body = response.json()
        if body["status"] != "running":
            return body
        print(f"{body.get('completed', 0)} of {body.get('total', '?')} pages done", file=sys.stderr)
        time.sleep(2)


if __name__ == "__main__":
    pdf = sys.argv[1]
    result = wait(submit(pdf))
    if result["status"] != "completed":
        sys.exit(f"OCR ended with status {result['status']}")
    markdown = "\n\n".join(page["markdown"] for page in result["pages"])
    out = os.path.splitext(pdf)[0] + ".md"
    with open(out, "w") as f:
        f.write(markdown)
    usage = result["usage"]
    print(f"Wrote {out}: {usage['pages_processed']} pages, {usage['pages_failed']} failed")

python pdf_to_markdown.py paper.pdf

{
  "request_id": "01a165c4-d049-78e1-b194-ddd4016c515c",
  "status": "accepted",
  "location": "/inference/v1/ocr/01a165c4-d049-78e1-b194-ddd4016c515c"
}