# oomol-lab/pdf-craft

PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.

Repository: https://github.com/oomol-lab/pdf-craft
Canonical: https://ross.abutalabs.com/products/pdf-craft
Homepage: https://inkora.oomol.com/
Language: Python
License: MIT
License Family: permissive
Topics: document, ocr, pdf, deepseek-ocr
Last push: 2026-08-25T11:56:57+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 40
- inputs: {"age_days": 567, "days_push": 8, "days_rel": 6, "gap_med": 7, "n_releases_24m": 22}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6226, forks 442 (observed 2026-08-28T04:09:40.721655+00:00)

## What it is
pdf-craft is a Python library that converts PDF files into Markdown or EPUB, with a focus on scanned books and documents. It uses OCR (locally on GPU or via a remote vendor service) and an LLM for translation, handling tables of contents, footnotes, tables, formulas, and images.

## Use cases
- convert scanned book pdfs to markdown
- turn pdf into epub
- make scanned documents searchable
- ocr a scanned pdf book
- translate a pdf and write translation back into it
- extract tables and formulas from scanned pdfs

## When to choose
- you need to convert scanned books or academic documents into editable formats like Markdown or EPUB
- you want a Python library with both local GPU OCR and remote OCR service options
- you need PDF translation integrated into the conversion pipeline

## When to avoid
- you only need simple text extraction from digitally-born (non-scanned) PDFs
- you need a GUI-only tool with no programming
- you lack a GPU and cannot use a remote OCR service

## Facets
- artifact type: library
- maturity: active
- function: ocr, pdf, parser, nlp, llm-inference
- domain: pdf, files, developer-tools
- platform: python, cross-platform
- tags: pdf-conversion, epub, markdown, scanned-books, document-processing, translation, natural-language-processing, gpu

## Member repositories
- oomol-lab/pdf-craft (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:40.721655+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 2026-08-29T17:47:13.866316+00:00, confidence not recorded.
  - readme: https://github.com/oomol-lab/pdf-craft (fetched 2026-08-28T04:09:40.721655+00:00, sha b4a03cbe62af)
  - homepage: https://inkora.oomol.com/ (fetched 2026-08-29T08:43:31.009076+00:00, sha 2b06242a38e5)
  - registry_pypi: https://pypi.org/pypi/pdf-craft/json (fetched 2026-08-29T08:43:31.019048+00:00, sha f6edb921dfd1)
- Data as of 2026-08-30T08:39:29.467469+00:00.