Awesome GitHub RepositoriesDocument Conversion APIs

Pandoc is a universal document converter that translates content between a wide range of markup and binary formats. It functions by parsing input documents into a unified intermediate abstract syntax tree, which serves as the foundation for consistent manipulation and transformation across diverse output types. The system is distinguished by its modular reader-writer pipeline, which decouples input parsing from output generation to allow for granular control over document structure. Users can programmatically manipulate this intermediate tree through a robust filter system, supporting both ex

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

chineseocr_lite is a lightweight Chinese optical character recognition engine designed to detect text regions, analyze orientation, and convert Chinese characters from images into digital text. It supports both horizontal and vertical reading layouts and can be deployed as a web service for image uploads and result visualization. The system utilizes a multi-backend inference framework that supports ncnn, mnn, and tnn, allowing it to run across diverse hardware and platforms. It is specifically engineered for lightweight deployment on mobile and desktop environments through the use of small mo

A fast, helpful, and open-source document parser

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

Yao is an LLM agent framework and low-code web app builder designed for orchestrating autonomous AI agents. It provides a platform to design, deploy, and coordinate agents with specialized personas that can plan tasks, utilize external tools, and execute multi-stage pipelines. The project distinguishes itself through a Model Context Protocol server for connecting assistants to external binaries and HTTP services, and a gRPC remote execution engine that allows agents to manage remote servers and devices. It includes a model-agnostic provider bridge that supports dynamic switching between vario

Megaparse is a document parsing tool and RAG data preprocessor designed to convert PDFs, Word documents, and presentations into clean text formats. It functions as a vision-based document extractor that recovers high-fidelity information from images and complex layouts to optimize data for large language model ingestion. The system employs multimodal AI and vision models to perform schema-preserving parsing, which maintains structural hierarchies such as tables and headers. It utilizes lossless structural transformation to turn layout-heavy binary files into text sequences while preserving th

PaddleX is a PaddlePaddle-based framework for building, deploying, and fine-tuning AI model pipelines, with pre-built support for computer vision, OCR, document analysis, and time series tasks. It offers a toolkit of ready-to-use pipelines for image classification, object detection, segmentation, and pose estimation, alongside an end-to-end OCR document analysis pipeline that extracts text, tables, formulas, and layout information. The platform also includes a dedicated time series forecasting pipeline for analyzing historical data to detect anomalies, classify patterns, and predict future val

Sparrow este o platformă LLM pentru extracția documentelor și un motor de inferență bazat pe viziune, conceput pentru a converti imagini și PDF-uri în date structurate validate. Funcționează ca un orchestrator de fluxuri de lucru agentice care înlănțuie sarcini de clasificare, extracție și validare în pipeline-uri multi-etapă. Sistemul se distinge printr-un strat de inferență agnostic față de backend, care gestionează modele pe GPU-uri locale, Apple Silicon și furnizori cloud. Utilizează grounding vizual bazat pe coordonate pentru a mapa textul extras la coordonate precise de tip bounding box și folosește direcționarea modelelor bazată pe indicii pentru a ghida atenția și a normaliza formatele de date. Platforma acoperă fluxuri de lucru de inteligență documentară, inclusiv procesarea specializată a tabelelor bazată pe imagini pentru a menține integritatea structurală și validarea bazată pe schemă pentru a verifica corectitudinea câmpurilor extrase. Oferă, de asemenea, un dashboard de analiză a documentelor pentru monitorizarea performanței API-ului, a analizei de utilizare și a stării sistemului. Arhitectura include un sistem de extensie bazat pe plugin-uri pentru integrarea bibliotecilor terțe utilizate în indexare și orchestrare.

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

Chonkie este o bibliotecă de chunking (segmentare) a textului concepută pentru pipeline-uri de retrieval-augmented generation (RAG). Funcționează ca un splitter semantic de text și un pipeline de ingestie RAG, transformând textul brut în segmente încorporate pentru stocare în baze de date vectoriale. Proiectul se distinge prin strategii de segmentare specializate, inclusiv un splitter de cod bazat pe AST pentru păstrarea limitelor logice în codul sursă și un splitter semantic de text care utilizează modele de embedding pentru a determina limitele bazate pe semnificație. De asemenea, oferă un ingestor pentru baze de date vectoriale pentru a automatiza generarea embedding-urilor și exportul acestora către diverse stocuri. Biblioteca acoperă o gamă largă de capabilități, inclusiv parsarea documentelor prin OCR și extragerea markdown, o varietate de metode de segmentare precum numărarea token-urilor și segmentarea ierarhică, și orchestrarea fluxului de lucru prin pipeline-uri reutilizabile. Suportă o gamă largă de integrări cu vector store-uri, inclusiv Qdrant, Milvus, Weaviate și Elasticsearch, precum și exportul datelor către JSON și seturi de date Hugging Face. Utilizatorii pot executa aceste operațiuni printr-o interfață în linie de comandă sau pot implementa sistemul ca serviciu API containerizat.

This project is an AI-powered screenshot manager and visual assistant designed for capturing screen content and processing it through large language models. It functions as an OCR translation application and screen annotation tool, allowing users to extract text from images and perform intelligent analysis of visual data. The software differentiates itself through an AI-driven OCR pipeline and the ability to convert screenshots into structured Markdown or HTML via layout-aware document transformation. It features a visual AI assistant capable of analyzing screen content and a prompt-engineere

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