bytedance/Dolphin

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

document-analysislayout-analysisocrparserpdfpdf-converterpdf-parserpythonvlm-ocr

License & maintenance

Custom or modified license that GitHub does not recognise: read the LICENSE file in the repository before using it in a product.

Last code push 6 months ago.

	Repository	Stars	Language	License	Activity
1	opendatalab/MinerUTransforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.	★ 82k	Python	Other	Active
2	ocrmypdf/OCRmyPDFOCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched	★ 35.1k	Python	MPL-2.0	Active
3	run-llama/liteparseA fast, helpful, and open-source document parser	★ 12.9k	Rust	Apache-2.0	Active
4	py-pdf/pypdfA pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files	★ 10.3k	Python	Other	Active
5	docling-project/doclingGet your documents ready for gen AI	★ 69.1k	Python	MIT	Active
6	wmjordan/PDFPatcherPDF补丁丁——PDF工具箱，可以编辑书签、剪裁旋转页面、解除限制、提取或合并文档，探查文档结构，提取图片、转成图片等等	★ 12.7k	C#	—	Active
7	getomni-ai/zeroxOCR & Document Extraction using vision models	★ 12.2k	TypeScript	MIT	Stale
8	hiroi-sora/Umi-OCROCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。	★ 48k	Python	MIT	Slowing