neosun100 / DeepSeek-OCR-WebUI
Self-hosted DeepSeek-OCR-2 WebUI & API — vLLM / transformers on NVIDIA, Apple Silicon & CPU, per-page quality checks, PDF streaming, MCP
Why this job: topics: document-parsing, ocr
What it does
All screenshots are generated by frontend/scripts/screenshots.mjs against a real backend (DeepSeek-OCR-2 on an Apple M5 Max). The demo document is generated by scripts/make_demo_docs.py.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 days ago
- Stars
- 446
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v5.0.0
- Released 3 days ago
- Built with
- TypeScript
- 51% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 96% closed
- 2 still open
- Pull requests
- 2 merged
- 3 waiting
- Releases
- 1
- 1 in the last year
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- TypeScript 51%
- Python 20%
- HTML 18%
- Vue 8%
Topics
- apple-silicon
- batch-processing
- computer-vision
- deepseek
- deepseek-ocr-2
- document-parsing
- fastapi
- image-recognition
- mcp
- modern-ui
- ocr
- python
Project record
- JobRAG and search
- StatusListed
- Commits254
- Forks94
- Watching7
- Stars in 28 days+2
- CreatedOct 20, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026