Word bounding boxes and confidence

Every recognized word comes with a location and a confidence score. Here's how to use them.

Overview

This is one of those capabilities that quietly saves teams hours a week. word boxes and confidence, built into the platform.

How to use it

from docen import Docen

client = Docen(api_key=DOCEN_API_KEY)
result = client.parse("document.pdf")

print(result.markdown)
print(result.json)

• Works on the same inputs as the rest of the platform.
• Returns portable Markdown, HTML, and JSON.
• Ships with word-level boxes and confidence.

Notes

As always, outputs are structured and portable, so whatever you build on top isn't locked to us. If you have a format in mind, chances are we already support it.

Want to see it on your own documents? Open the playground or reach out — we're happy to run a sample with you.