AI Document OCR
AI Document OCR is a app in the osFoundry community catalog. Document OCR — extract text from scanned documents, photos, PDFs. Layout-aware (preserves columns, headers, tables). 50+ languages. Powered by docTR (mindee). CPU is the default; GPU accelerates batch processing.
Details
- Workspace: osfoundry
- Category: PRODUCTIVITY
- Pricing: Free
- Access: Community
Documentation
# AI Document OCR
Document OCR, powered by docTR.
## CPU-friendly
docTR uses TensorFlow / PyTorch with quantised models that run reasonably on CPU (~1-3 seconds per page). Not all AI apps in this batch are CPU-friendly — docTR is among the easiest to run without GPU.
## Features
- Layout analysis (preserves columns, headers, tables, lists)
- 50+ languages
- Multi-page PDF input
- Output formats: JSON (with bounding boxes), plain text, hOCR, Markdown
- Confidence scoring per word
- REST API
- Streamlit + Gradio demo apps
## Packaging
Gradio wrapper around upstream docTR. Models cached at `/data`.
How to use AI Document OCR in osFoundry
Install AI Document OCR into your workspace in one click, then fork it in osStudio to customise the prompts, tools, or configuration for your stack. Anyone in your workspace can pick up where you left off.
Other apps from the community
- CRM — Customer relationship management with contacts, deals, and pipeline tracking.
- Kanban Board — Drag-and-drop task board with swimlanes, labels, and team assignments.
- Helpdesk — Ticket triage and customer support inbox with SLA tracking.
- Page Builder — Block-based page editor with publishing to public URLs.
- Website Builder — Multi-page site builder with CMS, templates, and custom domains.
- Storefront — E-commerce storefront with product catalog, cart, and checkout.