Awesome GitHub RepositoriesDocument Segmenters

DeepCode is an agentic development framework designed to orchestrate autonomous AI agents for software engineering tasks. It functions as a multi-agent workflow orchestrator that translates natural language requirements into functional codebases by coordinating specialized agents for architectural planning, intent analysis, and implementation. The platform integrates multiple language models to power these automated routines, providing a unified environment for complex development projects. The system distinguishes itself through its ability to transform academic research papers into executab

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

Easy-dataset is a comprehensive platform designed for the end-to-end management of machine learning datasets, specifically tailored for language and vision model fine-tuning. It functions as a centralized environment for the entire data lifecycle, encompassing the automated generation of synthetic training data, the structural organization of document collections, and the systematic annotation of individual data points. The platform distinguishes itself through its integrated evaluation and orchestration capabilities. It provides a dedicated suite for benchmarking models, featuring blind side

DataHub is a metadata management platform designed to unify technical, operational, and business context across diverse data ecosystems. By utilizing a graph-based metadata model and an event-driven ingestion architecture, it creates a centralized source of truth that maps complex data relationships, lineage, and ownership. This foundational framework enables organizations to maintain a synchronized view of their data landscape, supporting both human-led discovery and automated data operations. The platform distinguishes itself through its focus on grounding artificial intelligence and autono

Grobid est un système de machine learning conçu pour transformer les publications académiques et scientifiques PDF en XML structuré. Il fonctionne comme un analyseur PDF vers XML et un extracteur de métadonnées savantes, identifiant et normalisant les titres, auteurs, affiliations et références bibliographiques des articles de recherche. Le système utilise un segmenteur de documents par deep learning pour diviser les PDF bruts en régions fonctionnelles et emploie un résolveur de références bibliographiques pour faire correspondre les citations avec des registres externes pour l'enrichissement des métadonnées et la résolution de DOI. Il prend en charge un pipeline complet d'entraînement de modèles de machine learning, permettant la génération de corpus d'entraînement annotés, le réentraînement de modèles et l'exportation de binaires de modèles. Le projet couvre un large éventail de capacités d'extraction, y compris l'analyse des en-têtes de documents, la structuration du corps du texte intégral et l'identification d'entités spécifiques au domaine comme les informations de financement et les citations de brevets. Il fournit également des outils d'analyse spatiale pour l'extraction de boîtes englobantes et le mappage de coordonnées afin de synchroniser les étiquettes sémantiques avec la mise en page PDF originale. L'application peut être déployée via des images conteneurisées et inclut des utilitaires en ligne de commande pour le traitement par lots multi-threadé de grandes collections de documents.

GPAC is an open-source multimedia framework built around a pluggable filter graph pipeline, where modular processing units called filters connect into a directed graph to handle media workflows. At its core, the framework centers all media packaging and manipulation on the ISO Base Media File Format (ISOBMFF), with specialized tools for reading, writing, fragmenting, and encrypting MP4 and related containers. It also provides a declarative scene graph composition system for describing interactive multimedia scenes using MPEG-4 BIFS, X3D, SVG, or VRML syntax, alongside a hardware-accelerated re