#4 · Primary category: Knowledge Base & RAG

docling

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

Get your documents ready for gen AI

Project last updated:08/28/26

GitHub Stars

65.7K

Forks

4.7K

Contributors

289

License

MIT

Why we included this project

Docling is a document parsing library that handles the files people actually have: PDFs, DOCX, PPTX, XLSX, HTML, EPUB, and even audio and video. It converts them into a single structured document model that exports to Markdown, HTML, or lossless JSON. Reading order, table structure, layout, and formulas survive the conversion, so you feed a vector store or an agent real structure instead of a flat text dump. It runs locally for sensitive or air-gapped data, includes OCR for scanned pages, and has ready-made integrations with LangChain, LlamaIndex, and Haystack, which keeps the glue code minimal. For teams building knowledge bases, document Q&A, or agent workflows over real-world files, that structured output is usually the difference between a working pipeline and one that needs constant cleanup.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category