signalGitHub Trending2026-09-21
docling-project/docling
Docling is an open-source document processing tool that parses PDF, DOCX, PPTX, XLSX, HTML, EPUB, email, audio, and other formats, with advanced PDF understanding of layout, reading order, tables, formulas, and image classification, exporting to Markdown, HTML, and lossless JSON. It supports local/air-gapped execution, OCR, VLM models like GraniteDocling, and integrates with LangChain, LlamaIndex, Crew AI, and Haystack. Install via `pip install docling` (Python 3.10+; 3.9 dropped in v2.70.0) and convert documents with `docling [URL]` to generate a .md file, or use the Python `DocumentConverter` API.
- why now
- Docling now parses video files.
- topic
- AI Tools & Agent Workflows
- source
- GitHub Trending
#Docling#GenAI
score
score 8 out of 10. 0-10: how dense the facts are, multiplied by how much you can do with them after reading. 8+ means the topic's evidence bar is met: benchmarks and availability for a new model, amount and investors for a funding round, revenue figures for a solo-money story. Below 5 an item does not enter the digest. A press release scores 3 or less, a reprint loses 2, anything older than 14 days loses 1, a headline that misleads loses 3.
read the source