GitHub Repo · Documents & PDFs
Docling
Turns PDFs, Word files and scans into clean text that AI tools can use.
What Docling does
Docling converts PDFs, Office documents, images and HTML into structured Markdown or JSON, keeping tables, headings and reading order. It runs locally and is commonly used to prepare documents for AI search and chatbots.
Best for
- Preparing documents for AI chat
- Extracting tables from PDFs
- Processing files without uploading them
How small businesses use Docling
- Convert supplier PDFs into spreadsheets
- Feed manuals into a document chatbot
- Extract text from scanned paperwork
Docling: common questions
Who should use Docling?
Docling suits preparing documents for AI chat, extracting tables from PDFs and processing files without uploading them.
When should you choose something else instead of Docling?
Docling runs from code or the command line, so it needs some technical comfort. If that matters for your business, compare other options such as Stirling-PDF, Paperless-ngx and Documenso.
Is Docling free?
Docling pricing: Free and open source. Pricing changes often, so confirm current plans on the official repository or website before you buy.
Can a small business self-host Docling?
Yes. Docling is open source on GitHub, and its setup level is intermediate. You will need a computer or server to run it and someone to keep it updated and backed up, or you can use a hosted option if one is offered.
Other options in Documents & PDFs
Self-hosted PDF toolkit: merge, split, convert, OCR and sign.
Scan, OCR, auto-tag and search all your paperwork.
Open-source e-signatures, a DocuSign alternative.
Convert PDFs, Office files and more into AI-ready Markdown.