Libraries & frameworks
docling
docling-project/docling
A document parsing and conversion framework that turns PDFs, Office files, HTML and more into structured Markdown or JSON, with LangChain, MCP and API-server integrations.
Topics
Related projects
opendataloader-pdf30.3kAn open-source PDF parser for AI-ready data and accessibility, extracting structured Markdown, JSON and HTML with bounding boxes, OCR and automatic tagged-PDF generation.
indra1.6kA lightweight CPU OCR and document-parsing application that turns PDFs and images into Markdown, text, or JSON with layout, language, and handwriting support.
dedoc735An AI-powered document parsing system that converts Office files, PDFs, and scans into structured content with tables.
docsagent578⚡ DocsAgent - give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, local docs on the road). Native C++ search core: BM25 + passage ranking in ~15 ms. MCP server for Claude, Cursor, Cline & any MCP client.
PHPWord7.6kPHPWord is a pure PHP library for creating and reading Word documents. It lets developers generate DOCX, ODT, RTF, HTML and PDF files from PHP code with a rich set of formatting features.
pdf-to-image1.5kspatie/pdf-to-image is a PHP package that converts PDF pages into JPG, PNG or WebP images via Imagick and Ghostscript, with control over page selection, DPI, size and quality.