docling

Get your documents ready for gen AI

51.9k
Stars
+8.5k
Gained
19.6%
Growth
Python
Language

💡 Why It Matters

Docling addresses the challenge of preparing documents for generative AI applications, making it easier for engineering teams to convert various document formats into usable data. Backend/API teams and ML/AI teams particularly benefit from its capabilities, as it streamlines the document parsing process, allowing for quicker integration into AI workflows. With a solid user base and a growing number of stars, Docling is a production-ready solution that demonstrates maturity in its development. However, it may not be the right choice for teams requiring extensive customisation or those working with highly specialised document formats that are not supported.

🎯 When to Use

Docling is a strong choice when teams need a reliable open source tool for engineering teams to convert documents into formats suitable for AI processing. Teams should consider alternatives if they require advanced features or support for niche document types not covered by Docling.

👥 Team Fit & Use Cases

Docling is ideal for backend/API teams, DevOps/platform teams, and ML/AI teams who need to integrate document parsing into their systems. It is commonly used in products that involve AI-driven document processing, content management systems, and data extraction tools.

🎭 Best For

🏷️ Topics & Ecosystem

ai convert document-parser document-parsing documents docx html markdown pdf pdf-converter pdf-to-json pdf-to-text pptx tables xlsx

📊 Activity

Latest commit: 2026-02-02. Over the past 85 days, this repository gained 8.5k stars (+19.6% growth). Activity data is based on daily RepoPi snapshots of the GitHub repository.