# Bogdanovich77/DeekSeek-OCR---Dockerized-API

Repository: https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API
Canonical: https://ross.abutalabs.com/products/deekseek-ocr-dockerized-api
Language: Python
License Family: other
Last push: 2025-10-22T19:32:31+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 48, release rhythm 35, longevity 22
- inputs: {"age_days": 316, "days_push": 315, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1091, forks 139 (observed 2026-08-28T04:03:32.850250+00:00)

## What it is
A Dockerized REST API and batch processing scripts that convert PDF documents to Markdown using the DeepSeek-OCR model behind a FastAPI backend. It requires an NVIDIA GPU with at least 12GB VRAM and provides health checks plus multiple processing modes (markdown, plain OCR, custom prompts).

## Use cases
- convert pdf documents to markdown
- self-hosted ocr api for pdfs
- batch extract text from pdf files
- run deepseek-ocr in docker
- ocr scanned documents into markdown
- serve an ocr endpoint for my app

## When to choose
- you need a self-hosted OCR service with a REST API
- you have an NVIDIA GPU with 12GB+ VRAM and want Docker deployment
- you want batch conversion of PDFs to Markdown preserving structure

## When to avoid
- you have no CUDA-capable GPU
- you need a lightweight CPU-only OCR solution
- you want a managed cloud OCR service

## Facets
- artifact type: service
- maturity: active
- function: ocr, pdf, http-server, machine-learning
- domain: pdf, artificial-intelligence, developer-tools
- platform: python, windows
- tags: deepseek-ocr, pdf-to-markdown, fastapi, self-hosted, document-conversion, docker, linux, gpu

## Member repositories
- Bogdanovich77/DeekSeek-OCR---Dockerized-API (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:32.850250+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 2026-08-30T06:49:05.132952+00:00, confidence not recorded.
  - readme: https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API (fetched 2026-08-28T04:03:32.850250+00:00, sha 5aa773275d7c)
- Data as of 2026-08-30T08:39:29.467469+00:00.