Projects sharing features with Pdf Craft

Marker is an LLM-powered document parser and OCR pipeline designed to convert PDFs and unstructured files into structured markdown, JSON, and HTML. It functions as a data preprocessor that transforms complex documents into machine-readable formats while preserving tables, equations, and layout structures. The system utilizes large language models to refine OCR accuracy, clean mathematical notation, and merge fragmented tables across multiple pages. It employs model-based layout analysis to predict block types and bounding boxes, ensuring a more precise conversion of document elements. Capabi

Grobid is a machine learning system designed to transform academic and scientific PDF publications into structured XML. It functions as a PDF to XML parser and scholarly metadata extractor, identifying and normalizing titles, authors, affiliations, and bibliographic references from research papers. The system utilizes a deep learning document segmenter to divide raw PDFs into functional regions and employs a bibliographic reference resolver to match citations against external registries for metadata enrichment and DOI resolution. It supports a full machine learning model training pipeline, al

PyMuPDF is a comprehensive PDF manipulation library and document analysis tool. It serves as a text extraction tool, OCR engine, and image converter, providing a programmatic interface to edit, merge, split, and optimize PDF and Office documents. The project distinguishes itself through high-performance capabilities, including the use of C-bindings for low-level manipulation and parallelized page processing to accelerate workloads. It provides specialized conversion paths, such as transforming PDF content into Markdown for retrieval-augmented generation and large language model pipelines. It

This project provides a foundational framework and reference implementation for executing causal language modeling and multimodal reasoning on local systems. It includes a set of core components for managing model assets, a fine-tuning framework, and structural definitions required to instantiate transformer-based architectures. The system is distinguished by its ability to process combined text and image inputs through multimodal transformer models for visual reasoning and document analysis. It also supports the deployment of quantized models, reducing memory footprints through low-precision

Kreuzberg is a document extraction engine that converts PDFs, Office files, images, and over 90 other formats into clean, structured text and metadata. It is built around a compiled Rust core that can be used as a native library, a command-line tool, a REST API server, or a WebAssembly module for browser-based processing. The system is designed to run entirely on self-hosted infrastructure, with no data leaving the user's environment. What distinguishes Kreuzberg is its breadth of integration surfaces and its pipeline architecture. It exposes extraction capabilities through native bindings fo

Tesseract is a neural network-based optical character recognition engine designed to convert scanned images and digital documents into machine-readable, searchable text. It functions as both a command-line utility for automating large-scale digitization workflows and a cross-platform library that can be embedded into desktop, mobile, or server-side applications. By utilizing long short-term memory networks, the engine provides robust text extraction across more than one hundred languages and dozens of scripts. The project distinguishes itself through a sophisticated document layout analysis f

Fusuma is a markdown presentation framework and static slide generator that transforms Markdown and MDX files into structured slide decks for web-based presentations. It functions as a technical content renderer and an interactive presentation tool, enabling the creation of slides from text-based source files. The project distinguishes itself as a speaker delivery suite, providing tools for presentation rehearsal such as voice recording, timing analysis, and rehearsal timelines. It includes a dedicated presenter view with speaker notes and supports real-time slide annotations and live comment

Nougat is a neural OCR system and LLM document parser designed to convert images of academic PDF documents into structured markdown text and mathematical formulas. It functions as a PDF to markdown converter that uses deep learning to handle layout and formula recognition. The project provides a document training pipeline for generating datasets and training neural networks to recognize specific academic document styles. This includes utilities for training dataset generation, neural model training, and model checkpoint management to ensure reproducible deployment. The system covers a broad

Zerox is a multimodal document parser and OCR tool that uses vision models to convert PDF files and images into structured Markdown text. It functions as a visual layout extraction engine, leveraging large multimodal models to digitize documents while maintaining their original structural formatting. The system differentiates itself through the use of coordinate-based element mapping and multimodal layout analysis to identify structural elements like tables, charts, and headers. It utilizes rasterization to convert vector PDF pages into high-resolution bitmaps, ensuring consistent input for t

MinerU is a document parsing pipeline designed to transform unstructured files into machine-readable, structured data. It utilizes deep learning models to perform layout analysis, identifying document regions and extracting complex content such as mathematical expressions. By combining these neural network inferences with geometric heuristics, the system reconstructs the reading order and structural hierarchy of documents to ensure accurate data representation. The project distinguishes itself through a multi-stage processing workflow that integrates layout detection, optical character recogn

Pix2Text is an optical character recognition system and document conversion tool designed to transform images and PDFs into Markdown. It functions as a multilingual OCR engine supporting over 80 languages, a LaTeX formula recognizer for mathematical notations, and a parser integrated with vision language models. The project utilizes a hybrid pipeline to separate plain text from mathematical formulas and tabular structures within a single pass. It converts recognized formulas into LaTeX expressions and transforms detected tables and layouts into structured Markdown formatting. The system incl

dots.ocr is a suite of software utilities for document layout analysis, multilingual optical character recognition, and scene text digitization. It functions as an engine for extracting digital text and structured layout data from images and PDFs across various human scripts. The project includes a specialized transformer for converting charts, diagrams, and chemical formulas from raster images into scalable vector graphics. It also provides a pipeline to transform extracted text and structural layout from documents and web screenshots into formatted Markdown files. The system covers capabil

Bookdown is a scientific publishing framework and multi-format document processor designed for authoring technical long-form content. It functions as an R Markdown book generator and static site generator, transforming markup files into cohesive books and reports. The system distinguishes itself through its ability to handle complex scientific document authoring, featuring integrated LaTeX typesetting, theorem environments, and automated cross-referencing for equations, figures, and theorems across multiple chapters. It enables multi-format e-book production, allowing a single project to be r

This project is a PDF data extraction tool and document preprocessor designed to convert PDF files into structured formats such as Markdown, JSON, and HTML. It functions as an OCR document parser for scanned files, an accessibility automator for generating PDF/UA compliant metadata, and a loader for AI orchestration frameworks like LangChain. The software distinguishes itself through specialized handling of complex document elements, including the conversion of mathematical formulas into LaTeX and the generation of natural-language descriptions for charts and images. It utilizes recursive seg

pdfminer.six is a programmatic tool for extracting text, layout information, and metadata from PDF documents into machine-readable formats. It functions as a document parser that converts internal PDF objects and structures into accessible data objects for analysis. The project includes utilities for decrypting RC4 and AES encrypted files to enable content extraction. It also provides a layout analyzer to identify fonts, colors, and text locations to determine the organizational structure of pages. The system covers a broad range of extraction capabilities, including the retrieval of embedde

rmarkdown is a dynamic document generator and markdown rendering engine used to create reproducible reports, analysis, and websites. It functions as a literate programming tool that weaves narrative text with live executable code and data, ensuring that visual results are tied directly to the source code. The project serves as a multi-format rendering engine and content publisher, utilizing a Pandoc-based conversion framework to transform a single source file into diverse outputs such as PDFs, HTML pages, and presentation slides. It integrates with Knitr to execute code blocks and capture out

Sphinx is an extensible documentation framework and multi-format document publisher. It serves as a technical content organizer that converts reStructuredText markup and Python source code comments into structured documentation for technical projects. The system transforms a single set of markup files into multiple output formats, including HTML, LaTeX, EPUB, and Texinfo. It functions as a Python API documentation tool, extracting documentation directly from source code to maintain synchronized technical reference manuals. The framework organizes complex information into hierarchies with aut

Parsr is an unstructured data extractor and document parsing pipeline that converts raw files and images into cleaned, machine-readable formats. It functions as a document layout analyzer and a pipeline for extracting structured data and labels using large language models. The system includes a document parsing visualizer, providing a graphical interface to upload documents and inspect the resulting structured data output. The project covers document digitization workflows, including layout analysis to detect headings, tables, and lists, and automated data entry through the cleaning and enri

Tinymist is a comprehensive suite of tools for Typst document authoring, serving as a language server, document compiler, and project manager. It provides a standardized language service via the Language Server Protocol to enable editor features such as autocompletion, navigation, and semantic highlighting. The project distinguishes itself by integrating a TCP-based live preview server for real-time visual rendering and an advanced static analysis tool that utilizes abstract syntax trees and bidirectional type checking. It also includes a project management system capable of handling multi-fi

This project is an AI-powered resume builder and JSON-based document editor used for creating professional curriculum vitaes. It combines a template-driven design tool with a multi-format document exporter to convert digital resumes into high-definition PDF, image, Markdown, and raw data formats. The system utilizes JSON schemas to define and render structured resume components and layouts. It integrates artificial intelligence to generate, polish, and translate resume text, and provides quality analysis to identify profile weaknesses and suggest optimizations. The platform covers visual doc

Doxygen is a source code documentation generator and multi-language API reference tool. It extracts annotated comments from source code to create structured technical manuals and searchable software libraries in formats including HTML, LaTeX, and PDF. The project functions as a static code analysis visualizer, generating call graphs, class diagrams, and inheritance hierarchies to illustrate codebase structure. It also serves as an XML documentation export engine, producing structured metadata that can be transformed via XSLT or third-party tools. Beyond API extraction, the tool provides a Ma

Asciidoctor is a Ruby-based text processing engine and command-line toolchain designed to convert AsciiDoc content into structured publishing formats, including HTML5 and DocBook 5. It functions as a static content publishing toolchain that transforms raw source files into formatted documents. The system utilizes a pluggable converter interface and template-driven output, allowing the default conversion logic to be overridden via custom converters or templates. This enables the generation of specific document structures and the export of content into various publishing formats for diverse dis

Docling is a multimodal content converter and document parser designed to transform PDFs, Office files, and HTML into structured Markdown or JSON for generative AI applications. It functions as an OCR document processor and a PDF layout analyzer that extracts tables, charts, and hierarchical structures while preserving the original page layout. The system operates as a local-first inference engine, allowing for the processing of sensitive data in air-gapped environments without external network connectivity. It can also be deployed as an API or a Model Context Protocol server to provide parsi

Bisheng is an enterprise AI framework and LLM DevOps platform designed to manage the full lifecycle of large language models. It provides a unified system for dataset curation, supervised fine-tuning, model versioning, and performance evaluation. The platform features a visual workflow orchestrator for building retrieval-augmented generation pipelines and complex task sequences using flowcharts with conditional logic and human intervention points. It also includes an AI agent framework that uses a specialized guidance language to embed domain expertise and professional business logic into aut

HackMyResume is a command-line tool that generates polished résumés and CVs in multiple formats from a single JSON or YAML data source. It validates résumé documents against the FRESH or JSON Resume schema, converts between these two formats, and produces output in HTML, Markdown, LaTeX, MS Word, PDF, plain text, JSON, XML, and YAML. The tool supports custom themes through a plugin architecture, allowing users to apply visual styling via Handlebars templates and register custom helpers for extended template logic. It can merge multiple résumé JSON files into one, overriding generic data with

Dolphin is a multimodal layout analyzer and image-to-structure converter that transforms photographed or digital document images into machine-readable structured data. It functions as an LLM document parser, utilizing vision-language models to simultaneously predict spatial layout and text content. The system is designed as a concurrent document processor, employing parallel document parsing to process multiple elements across distributed compute nodes. This high-throughput approach reduces the total time required to convert large volumes of images into structured formats. The project covers

ChatPaper is a suite of AI agents and utilities designed for academic literature automation, manuscript editing, and research assistance. The system functions as a research assistant that summarizes, translates, and analyzes scholarly papers, while providing specialized tools for converting academic PDFs into structured markdown to preserve formulas for analysis. The project features a literature survey automator that crawls research repositories and synthesizes domain reports, alongside a research mind map generator that transforms linear document content into non-linear node-based maps. It