Awesome GitHub RepositoriesStructured Document Extraction

PaddleOCR is a comprehensive optical character recognition framework designed for detecting and transcribing text from images and documents into structured, machine-readable formats. It provides a modular computer vision pipeline that decouples image preprocessing, text detection, and character recognition into independent, configurable stages. This architecture supports automated document digitization and multilingual text recognition, capable of identifying text in over one hundred languages across diverse environments ranging from scanned documents to industrial scenes. The framework disti

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

PageIndex is an agent-ready knowledge engine that processes documents into hierarchical tree structures to enable reasoning-based information retrieval. By organizing content into logical trees rather than relying on traditional vector database chunking, the platform preserves the original structure and flow of complex documents. It functions as a Model Context Protocol server, allowing external AI agents to connect to and query indexed knowledge bases through standardized communication protocols. The platform distinguishes itself by using vision-language models to process raw document images

This project is a high-performance headless browser engine designed for scalable web automation, data extraction, and AI agent integration. It provides a specialized environment that allows autonomous agents and testing frameworks to interact with web content through standardized remote control protocols. By executing pages in a lightweight, headless state, the engine minimizes resource consumption while maintaining the ability to perform complex navigation and dynamic content rendering. The platform distinguishes itself through deep integration with AI-centric communication layers and advanc

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

Kotaemon is an orchestration framework designed for building modular, agentic workflows that integrate document processing, retrieval-augmented generation, and multi-step reasoning. It provides a comprehensive platform for developing document-based question answering systems, allowing users to chain language models, prompt templates, and external tools into complex, automated pipelines. The system distinguishes itself through a highly modular architecture that emphasizes component-based composition and schema-driven data exchange. It supports autonomous agents capable of decomposing complex q

This project is a comprehensive framework and toolkit for developing, optimizing, and deploying transformer-based models across multimodal, document intelligence, and natural language processing tasks. It provides a unified neural architecture that processes text, vision, audio, and document layout data through a shared set of weights, enabling researchers and developers to build foundational models that align cross-modal representations. The platform distinguishes itself through advanced training and inference strategies designed for large-scale deep learning. It incorporates specialized mec

Qwen2.5-VL est un transformeur multimodal autorégressif conçu pour traiter des séquences entrelacées de jetons de texte et visuels. Il intègre des intégrations de caractéristiques visuelles dans un espace de modèle de langage partagé pour effectuer un raisonnement transmodal et générer des réponses cohérentes ou du code de mise en page structuré. Le projet se distingue par la cartographie vision-langage-action, lui permettant de percevoir des interfaces visuelles et de traduire cette perception en commandes exploitables pour faire fonctionner des écrans numériques et du matériel robotique. Il utilise un encodage d'image à résolution dynamique et une indexation vidéo à trame temporelle pour gérer diverses tailles d'image et des séquences visuelles de longue durée. Le modèle couvre une large surface de capacités, notamment la reconnaissance optique de caractères multilingue pour la numérisation de documents, la mise à la terre spatiale pour localiser des objets via des boîtes englobantes, et l'analyse de contenu vidéo long format. Il prend également en charge le raisonnement mathématique multimodal pour résoudre des problèmes en utilisant des graphiques et des diagrammes, et étend sa compréhension à une longueur de contexte d'un million de jetons.

Qwen2-VL is a multimodal large language model and vision language model designed to process and reason across text, images, and video content. It functions as a visual reasoning engine and a visual agent framework, capable of interpreting visual data to perform object detection, document parsing, and spatial reasoning. The model is distinguished by its ability to act as a video understanding model, processing hour-long videos with second-level indexing and event recall. It further differentiates itself through a visual agent capability that interacts with software interfaces and robotic hardw

Qwen3-VL is a multimodal vision-language model designed to process and reason across images, videos, and text. It functions as a computer vision framework capable of identifying objects, extracting structured data from documents, and interpreting spatial elements within visual media. The system operates as an automated user interface interaction agent, interpreting screen data to navigate software and mobile applications. By utilizing a unified transformer architecture, it performs complex visual reasoning to execute user-defined tasks without manual input. Beyond interface navigation, the m

Unstructured is an enterprise-grade data orchestration engine designed to transform raw, unstructured files into structured, machine-readable formats. It functions as a comprehensive platform for document ingestion, partitioning, and enrichment, specifically engineered to prepare complex data for retrieval-augmented generation and agentic AI workflows. The platform distinguishes itself through its sophisticated document processing strategies, which combine rule-based extraction with vision-language models to handle diverse file layouts, tables, and images. It provides a modular architecture t

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

A fast, helpful, and open-source document parser

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

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

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

DocTR is a deep learning OCR library built on PyTorch that detects and transcribes text in document images using a two-stage detection-recognition pipeline. It provides a complete framework for building and deploying OCR pipelines with pretrained models available through the Hugging Face Hub, and supports exporting trained models to ONNX format for cross-runtime deployment. The library offers end-to-end OCR pipelines that combine text detection and recognition to extract all text from document images or PDFs, with support for rotated page handling and varied text orientations. It includes cap

Layout-parser est un framework d'analyse d'image et d'analyseur de mise en page de document basé sur le deep learning. Il fournit une boîte à outils pour extraire des informations structurelles et des modèles de mise en page à partir de documents scannés et d'images numériques, les transformant en structures de données programmatiques pour une analyse automatisée. Le framework intègre la détection de mise en page avec la reconnaissance optique de caractères pour convertir les régions tabulaires en données lisibles par machine. Il utilise des réseaux de neurones pour identifier et classer les éléments structurels au sein des images de document sans dépendre de systèmes basés sur des règles manuelles. Le système couvre un large éventail de fonctionnalités d'analyse de document, y compris l'analyse de structure de document, l'extraction automatisée de tableaux et la représentation hiérarchique de mise en page. Il inclut également des outils de visualisation pour rendre les éléments détectés et les hiérarchies sur les images originales pour la vérification des résultats.

Sparrow est une plateforme d'extraction de documents par LLM et un moteur d'inférence basé sur la vision, conçu pour convertir des images et des PDF en données structurées validées. Il fonctionne comme un orchestrateur de workflow agentique qui enchaîne des tâches de classification, d'extraction et de validation dans des pipelines multi-étapes. Le système se distingue par une couche d'inférence agnostique au backend qui gère les modèles sur des GPU locaux, Apple Silicon et des fournisseurs cloud. Il utilise le "visual grounding" basé sur les coordonnées pour mapper le texte extrait à des boîtes englobantes précises et utilise un guidage par indices pour orienter l'attention et normaliser les formats de données. La plateforme couvre les workflows d'intelligence documentaire, incluant le traitement spécialisé d'images de tableaux pour maintenir l'intégrité structurelle et une validation basée sur des schémas pour vérifier l'exactitude des champs extraits. Elle fournit également un tableau de bord d'analyse documentaire pour surveiller les performances de l'API, les statistiques d'utilisation et l'état du système. L'architecture inclut un système d'extension par plugins pour intégrer des bibliothèques tierces utilisées dans l'indexation et l'orchestration.

sChandra is a document processing platform that converts images, PDFs, Word documents, spreadsheets, and other formats into structured output such as HTML, Markdown, or JSON while preserving layout. It can also extract specific data fields from invoices, contracts, or reports using user-defined JSON schemas, with citations back to source locations. The service supports form filling in PDF and image documents, document generation from Markdown, and extraction of tracked changes from Word files. The platform distinguishes itself with pipeline-based processing chains that combine multiple proces