# opendatalab/PDF-Extract-Kit

A Comprehensive Toolkit for High-Quality PDF Content Extraction

Repository: https://github.com/opendatalab/PDF-Extract-Kit
Canonical: https://ross.abutalabs.com/products/pdf-extract-kit
Homepage: https://pdf-extract-kit.readthedocs.io/zh-cn/latest/index.html
Language: Python
License: AGPL-3.0
License Family: copyleft
Last push: 2025-01-03T02:00:20+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 40, longevity 56
- inputs: {"age_days": 797, "days_push": 608, "days_rel": 691, "gap_med": 14.5, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9993, forks 750 (observed 2026-08-28T04:10:39.185358+00:00)

## What it is
PDF-Extract-Kit is a Python model toolbox for high-quality PDF content extraction, integrating state-of-the-art models for layout detection, formula detection and recognition, OCR, table recognition, and reading order. Its modular design lets developers combine components to build applications like document translation or Q&A, while end users seeking PDF-to-Markdown conversion are pointed to the companion MinerU tool.

## Use cases
- extract text and structure from complex pdf documents
- convert scanned pdfs to markdown with ocr
- detect and recognize math formulas in pdfs
- recognize tables in pdf documents
- detect document layout regions in pdfs
- build document qa or translation apps on top of pdf parsing models
- benchmark pdf parsing models on evaluation datasets

## When to choose
- you need modular, model-level building blocks for document parsing tasks
- you want state-of-the-art layout, formula, OCR, and table recognition models with benchmarks
- you are a developer building custom document processing applications
- you need fine-grained control over individual parsing stages

## When to avoid
- you just want a turnkey pdf-to-markdown converter - use MinerU instead
- you need a simple text extraction utility without deep learning models
- you cannot run GPU or heavyweight ML models in your environment
- your project requires a permissive license - this is AGPL-3.0

## Facets
- artifact type: library
- maturity: active
- function: ocr, pdf, machine-learning, parser, image-processing
- domain: pdf, machine-learning, developer-tools
- platform: python, windows
- tags: pdf-extraction, layout-detection, formula-recognition, table-recognition, document-parsing, model-toolbox, natural-language-processing, linux, macos, gpu

## Member repositories
- opendatalab/PDF-Extract-Kit (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:39.185358+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 2026-08-29T17:20:01.476065+00:00, confidence not recorded.
  - readme: https://github.com/opendatalab/PDF-Extract-Kit (fetched 2026-08-28T04:10:39.185358+00:00, sha cf05af0ba81f)
  - homepage: https://pdf-extract-kit.readthedocs.io/zh-cn/latest/index.html (fetched 2026-08-29T08:19:46.868449+00:00, sha 5f2cd7992d2c)
- Data as of 2026-08-30T08:39:29.467469+00:00.