Tag
Una librería en Rust que convierte documentos Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV y PDF a Markdown, disponible vía npm, Python y CLI, destacando su utilidad para LLMs.
John MacFarlane reflects on 20 years of Pandoc, the universal document converter, from its 2006 Haskell-based start to its global adoption in academic and writing tools.
Klartext is a free, privacy-focused web tool that converts PDFs, scans, photos, Word, Excel, and PowerPoint files into Markdown (plus JSON) entirely on its own server, with automatic deletion after 24 hours and no external AI/OCR services.
Marker is an open-source tool that converts PDFs, images, and other document formats to markdown, JSON, chunks, and HTML quickly and accurately, with optional LLM enhancement.
Marker 2 is released, offering up to 5x faster and more accurate conversion of PDFs, images, and DOCX to markdown compared to mineru, docling, and liteparse.
Pandoc Lua Filters allow users to manipulate the Pandoc AST using Lua scripts, providing a lightweight alternative to JSON-based filters without external dependencies.
An open-source tool converts PDFs, DOCX, PPTX, XLSX, EPUB, and images to markdown at 122 pages per second, supporting tables, equations, and forms on GPU, CPU, or Mac.
This article introduces 5 open-source tools for converting documents into AI-readable formats: Stirling-PDF, MinerU, docling, marker, and OCRmyPDF, respectively targeting PDF editing, complex document conversion to Markdown, structured document output, high-precision PDF to Markdown, and OCR for scanned documents.
Introducing the open-source document conversion tool Pandoc, developed in spare time by philosophy professor John MacFarlane, supporting conversion between over 50 formats, free, open source, and fully local.
This article highlights Pandoc, a free and open-source document conversion tool created by UC Berkeley philosophy professor John MacFarlane. It converts between over 50 formats locally without uploading files, saving significant time and maintaining privacy.
Introduces five open-source tools (MarkItDown, MinerU, Docling, marker, surya) that convert PDFs, Office documents, etc., into Markdown or JSON for direct use with RAG or AI agents.
Microsoft released MarkItDown, an open-source Python library that converts any document to Markdown for use with LLMs.
Microsoft has launched the MarkItDown tool, which converts various document formats (such as PDF, Word, Excel) into Markdown, making it easier for large models and RAG systems to process enterprise data.
Microsoft open-sourced MarkItDown, a lightweight Python tool that converts PDF, Word, PPT, Excel, HTML, and images into clean, structured Markdown text in one go, ideal for AI summarization, data analysis, knowledge base construction, and more.
This tool allows users to convert documents (docx, PPT, pdf, md) into HTML format, and edit them using an AI agent CLI. It supports multiple output formats, is local-first, and open source.