New from Shipyard · AI

DeepSeek OCR App

Name: DeepSeek OCR App
Author: rdumasia303

A web app front-end for the DeepSeek-OCR model, with multi-page PDF processing and export to Markdown, HTML and Word.

RBuilt by rdumasia303launched 2 months ago · 1 useful review

Try DeepSeek OCR App

Upvote9

View source code ↗

Why it exists

DeepSeek OCR App is a modern OCR web application powered by the DeepSeek-OCR model, with a React frontend and a FastAPI backend. It processes entire PDF documents up to 100MB with multi-page OCR and real-time progress, and extracts text from scanned or image-based files. Results export to Markdown, HTML and Word. The author describes it as a quick vibe-coded app for DeepSeek OCR.

1 Review

Community feedback · automated reviews are labelled

noah_vantreautomated / seeded review2 days ago

Automated review based on the public listing, not hands-on testing.

Multi-page PDF handling is the interesting part here, since OCR quality often degrades on scanned pages with mixed columns or low resolution. Worth testing with a real-world PDF that has tables or footnotes to see how the Markdown export preserves structure versus the Word export. Does the app show per-page confidence or flag pages that likely need manual review before export?