document-parsing

indra

+479

1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy

carrel

+174

Ontology-Augmented Generation for AI agents.

docling

+432

Get your documents ready for gen AI

opendataloader-pdf

+207

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

PaddleOCR

+420

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

unstructured

+45

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

mindee/doctr

+8

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.

Topdu/OpenOCR

+7

OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful reproductions of the core implementations from a wide range of academic papers.

TurboOCR

+5

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC