Docling: Get Your Documents Ready for Gen AI
summary
Open-source Docling converts PDFs, DOCX, PPTX, HTML, images and Markdown into a structured DocklingDocument unified format, extracts layout, tables, figures and reading order reliably, and exports to Markdown/JSON; it now has about 37,000 GitHub stars and ~2,000 active contributors. A 256M-parameter "SmallDocling" VLM performs one-shot layout segmentation, table reconstruction and figure description and can run on a phone. Production pieces include a CLI, dockling-serve REST API and MCP integrations with LlamaIndex, LangChain and LlamaStack.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 1:47What is Dockling
- 3:35Team and community
- 6:23Document conversion demo
- 7:26PDF parsing dangers
- 9:11Conversion pipeline features
- 11:35How processing works
- 13:01Enriching with AI
- 14:25Small Dockling model
- 16:54Agentic AI integration
- 18:49Live demo of MCP tools
- 21:04No-code Langflow integration
- 23:33Serve and OpenShift deployment
- 24:19Summary and call to action
- 25:09Q&A
related talks
35mDocling: Get your documents ready for gen AI
01h 25mLearn to Unlock Document Intelligence with Open-Source AI
01h 00mComplex Data Ingestion with Open Source AI
01h 19mLearn to Unlock Document Intelligence with Open-Source AI
31mConquering PDFs: document understanding beyond plain text
29mConquering PDFs- document understanding beyond plain text
26mAdvanced Document Parsing for AI Workflows
39mEnterprise-ready document processing for AI