# deepdoctection/deepdoctection

A Repo For Document AI

Repository: https://github.com/deepdoctection/deepdoctection
Canonical: https://ross.abutalabs.com/products/deepdoctection
Homepage: https://deepdoctection.readthedocs.io/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: document-parser, document-image-analysis, table-recognition, ocr, document-ai, document-understanding, python, document-layout-analysis, table-detection, pytorch, tensorflow, publaynet, pubtabnet, layoutlm, nlp
Last push: 2026-08-16T14:54:56+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 98, longevity 100
- inputs: {"age_days": 1728, "days_push": 17, "days_rel": 17, "gap_med": 7, "n_releases_24m": 58}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3248, forks 196 (observed 2026-08-28T04:07:51.830095+00:00)

## What it is
deepdoctection is a Python library for Document AI that orchestrates document layout analysis, table recognition, OCR, and document/token classification into configurable pipelines. It supports fine-tuning and inference with models like LayoutLM, LiLT, and Detectron2-based detectors, and integrates OCR backends such as Tesseract, DocTr, and AWS Textract.

## Use cases
- extract text and tables from scanned PDFs
- run OCR on document images
- detect document layout and tables
- classify documents with LayoutLM
- fine-tune document understanding models
- parse native PDF text

## When to choose
- building document extraction pipelines with layout analysis and OCR
- need table detection and recognition in documents
- want to fine-tune or use LayoutLM-family models
- processing scanned or PDF documents at scale in Python

## When to avoid
- need a simple one-line PDF text extractor without ML models
- working outside Python or without GPU/deep learning dependencies
- need a ready-made end-user application rather than a library

## Facets
- artifact type: library
- maturity: active
- function: ocr, pdf, machine-learning, computer-vision, nlp, image-processing, parser
- domain: artificial-intelligence, computer-vision, pdf, deep-learning
- platform: python, cross-platform
- tags: document-ai, document-layout-analysis, table-recognition, document-understanding, layoutlm, detectron2, pdf-parsing, natural-language-processing

## Member repositories
- deepdoctection/deepdoctection (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:51.830095+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 2026-08-29T18:43:54.134299+00:00, confidence not recorded.
  - readme: https://github.com/deepdoctection/deepdoctection (fetched 2026-08-28T04:07:51.830095+00:00, sha 8236f9d9a7c0)
  - registry_pypi: https://pypi.org/pypi/deepdoctection/json (fetched 2026-08-29T09:37:37.935693+00:00, sha 5a5c104d2682)
- Data as of 2026-08-30T08:39:29.467469+00:00.