dots.ocr is a single vision-language model developed for multilingual document layout parsing and optical character recognition. It can process complex page layouts, tables, and mixed-language content to produce structured outputs. The model is available on Hugging Face with open weights and supports integration through standard machine learning libraries.
In the Foundation models & chat space, Dots.ocr takes a focused approach. Accurately parsing complex document layouts and extracting text across multiple languages in a single model. Dots.ocr is an open-source project aimed at developers. The project is open source (MIT). Dots.ocr is available on the web, the command line, and API.
RedNote HiLab builds and maintains Dots.ocr, and the product first shipped in 2025. The project is developed in the open on GitHub with 9k stars. Among its 4 catalogued features are Document Layout Analysis, Multilingual OCR, and Vision-Language Model.
Latest indexed changes and source events
rednote-hilab/dots.ocr verified by the PulseGate indexer
Other apps tracked under the same category.
