# rdumasia303/deepseek_ocr_app

A quick vibe coded app for deepseek OCR

Repository: https://github.com/rdumasia303/deepseek_ocr_app
Canonical: https://ross.abutalabs.com/products/deepseek_ocr_app
Language: JavaScript
License: MIT
License Family: permissive
Last push: 2026-03-31T08:03:16+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 75, release rhythm 35, longevity 22
- inputs: {"age_days": 317, "days_push": 155, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1892, forks 310 (observed 2026-08-28T04:05:50.432105+00:00)

## What it is
A self-hosted OCR web application combining a React frontend with a FastAPI backend, powered by the DeepSeek-OCR model. It processes images and PDFs (up to 100MB) and exports results as Markdown, HTML, DOCX, or JSON while preserving formulas, tables, and images.

## Use cases
- extract text from scanned pdfs
- convert pdf documents to markdown
- ocr images with bounding boxes
- digitize scanned documents into word docx
- extract formulas and tables from academic papers
- pull structured data from invoices and forms

## When to choose
- you want a self-hosted OCR UI with a web interface
- you need multi-page PDF OCR with export to Markdown, HTML, DOCX, or JSON
- you want DeepSeek-OCR features like formula preservation and bounding boxes without writing code

## When to avoid
- you need a lightweight CLI or library to embed OCR in your own pipeline
- you require cloud-scale throughput or managed OCR APIs
- you lack GPU resources, since DeepSeek-OCR inference is compute-heavy

## Facets
- artifact type: application
- maturity: active
- function: ocr, pdf, image-processing, web-framework, http-server
- domain: computer-vision, pdf, web-development, developer-tools
- platform: python, self-hosted
- tags: deepseek-ocr, document-digitization, pdf-to-markdown, fastapi, react, formula-recognition, bounding-boxes, natural-language-processing, nodejs, web-server, docker

## Member repositories
- rdumasia303/deepseek_ocr_app (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:50.432105+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:12:58.217648+00:00, confidence not recorded.
  - readme: https://github.com/rdumasia303/deepseek_ocr_app (fetched 2026-08-28T04:05:50.432105+00:00, sha f8b28d5dc795)
- Data as of 2026-08-30T08:39:29.467469+00:00.