docling-api vs pdf-craft

Document conversion services and scanned-PDF workflows compared

docling-api is a self-hostable REST service that converts multiple document formats into Markdown, with synchronous and queued processing. pdf-craft is a Python library focused on scanned PDFs, with OCR workflows for Markdown, EPUB, and translated outputs.

docling-apipdf-craft
LanguagePythonPython
LicenseMITMIT
Stars1.7k6.4k
Forks425466
Last analyzedOct 3, 2026Oct 18, 2026

Key differences

  • docling-api accepts formats including office documents, HTML, CSV, and images, while pdf-craft focuses on scanned PDFs.
  • docling-api provides a FastAPI service with Celery and Redis for queued and batch jobs; pdf-craft provides synchronous and asynchronous Python APIs.
  • pdf-craft can create EPUBs with metadata and a table of contents, and supports translation workflows; docling-api focuses on Markdown conversion.
  • docling-api supports CPU-only or GPU deployments, while pdf-craft supports remote OCR and local OCR that requires suitable NVIDIA and CUDA hardware.
  • Both projects are written in Python and use the MIT license.

Choose docling-api if you…

  • need a self-hosted REST API for converting varied document formats to Markdown.
  • want synchronous or queued batch processing with job status tracking.
  • need optional CPU-only or GPU-enabled deployment choices.
Read the docling-api analysis →

Choose pdf-craft if you…

  • want to turn scanned PDFs into Markdown or EPUB publications.
  • need translation workflows for EPUBs or translated PDF output.
  • want a Python library with remote or local OCR options.
Read the pdf-craft analysis →

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.