OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Doctr

docTR is an open-source Python library for deep-learning document OCR. It detects text regions and recognizes their contents, with tools to read PDFs and images and return structured page results.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Doctr — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use docTR when building a Python document-processing workflow that needs OCR from PDFs or images and structured predictions for subsequent processing.

Who it is for

  • Python developers adding OCR to document-processing software.
  • Teams that need text locations or layout regions alongside recognized document text.

Documented uses

  • Extract text from scanned documents and PDFs.
  • Locate words and recognize their characters in document images.
  • Add page layout regions such as tables, titles, headers and footers to OCR results.
  • Export nested document predictions as a dictionary for JSON-oriented workflows.
Before you choose

Requirements & limits

The repository is public and identifies the project license as Apache-2.0. Installation requires Python 3.11 or higher and pip; installing from source also requires Git.

  • The documented installation prerequisite is Python 3.11 or higher.
  • The README describes PyTorch-powered OCR, while repository topics also associate the project with TensorFlow 2.
  • The pipeline separates text detection from recognition, with architecture choices for both stages.
  • PDF and image inputs are documented; webpage input is also shown and requires WeasyPrint.
  • Layout detection and visualization are additional options; visualization requires matplotlib and mplcursors.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install docTR from PyPI

Install the Python OCR library using its documented package route.

Before you start

  • Python 3.11 or higher
  • pip

Steps

  1. Install the package with pip install python-doctr.

  2. For the documented optional visualization, HTML and contrib dependencies, install python-doctr[viz,html,contrib] instead.

Expected outcome

The docTR package is installed, with optional extras available for the listed modules.

Guide limitations

  • This covers installation only; it does not configure or run an OCR workflow.
  • The optional extras are not required for the standard build.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
mindee/doctr · Official homepage title · retained in its source language
How we review sourcesSuggest a correction