docling vs pdf-craft
Document conversion tools compared
docling converts many document types into structured content for downstream applications, while pdf-craft focuses on turning scanned PDFs into Markdown and EPUB. Both are Python projects with OCR support, but pdf-craft also centers on translation and book-oriented publishing workflows.
docling: Parse Documents for AI Workflows
Docling converts documents from formats such as PDF, Office files, images, and audio into structured representations and exports. It suits developers building document-processing and generative AI pipelines that need format coverage, OCR, or local execution.
pdf-craft: Convert Scanned PDFs with DeepSeek OCR
PDF Craft is a Python library and online service for turning scanned books, research papers, and technical documents into editable Markdown or reader-friendly EPUB. Built around DeepSeek OCR, it also supports translation and translated PDF output.
| docling | pdf-craft | |
|---|---|---|
| Language | Python | Python |
| License | MIT | MIT |
| Stars | 68.3k | 6.4k |
| Forks | 5k | 466 |
| Last analyzed | Oct 3, 2026 | Oct 18, 2026 |
Key differences
- docling handles PDFs, office files, images, audio, video, email, and other formats; pdf-craft focuses on scanned PDFs.
- docling extracts document structure such as reading order, tables, code, and formulas into a unified representation; pdf-craft organizes OCR results into Markdown or EPUB.
- docling exports to several formats, including HTML and lossless JSON; pdf-craft offers EPUB creation, translation, and writing translated text onto source PDF pages.
- docling can run locally, including in air-gapped environments; pdf-craft supports remote OCR by default, while local OCR requires suitable NVIDIA GPU and CUDA setup.
- Both projects use Python and MIT licensing. docling has 68.3k stars and 5k forks, while pdf-craft has 6.3k stars and 460 forks.
Choose docling if you…
- need to process a varied collection of document formats through one interface.
- want structured extraction of PDF layout, tables, reading order, or formulas.
- need local processing or integrations with AI frameworks such as LangChain or LlamaIndex.
Choose pdf-craft if you…
- want to convert scanned books or documents into Markdown or EPUB.
- need translation workflows, including bilingual EPUBs or translated text written onto PDFs.
- want Python APIs for OCR and conversion with reusable saved extraction results.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.