Docling
Summary
Docling is an open-source project that aims to simplify document processing by parsing a wide range of formats (PDF, DOCX, EPUB, HTML, images, emails, etc.) and integrating with AI ecosystems. It offers a CLI, Python API, OCR support, and integrations with LangChain, LlamaIndex, and other tools, along with deployment as a service via an API server. The repository highlights features, quickstart guidance, licensing, and community resources.