SmolDocling is a web demo for processing document images with the SmolDocling vision-language model. Users can upload pages, tables, charts, code snippets, or formulas and request structured extraction or conversion into Docling format.
SmolDocling is a Computer vision, OCR & document AI project. It focuses on extracting structured text and document elements from images of pages, tables, charts, code, and formulas. It is built as an open-source project for developers, researchers, and document-processing users. SmolDocling costs nothing to use. It ships for the web, and it can be self-hosted.
docling-project builds and maintains SmolDocling. Key capabilities include image upload, batch processing, and text extraction.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do