🔥 Trending Repository: Dolphin

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

🔗 Repository URL: https://github.com/bytedance/Dolphin

📖 Readme: https://github.com/bytedance/Dolphin#readme

📊 Statistics:
🌟 Stars: 6.3K stars
👀 Watchers: 53
🍴 Forks: 516 forks

💻 Programming Languages: Python - Shell

🏷️ Related Topics:

#python #pdf #parser #ocr #pdf_converter #document_analysis #pdf_parser #layout_analysis #vlm_ocr

==================================
🧠 By: https://t.me/DataScienceM

🔥 Trending Repository: MinerU

📝 Description: Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

🔗 Repository URL: https://github.com/opendatalab/MinerU

🌐 Website: https://opendatalab.github.io/MinerU/

📖 Readme: https://github.com/opendatalab/MinerU#readme

📊 Statistics:
🌟 Stars: 45.7K stars
👀 Watchers: 183
🍴 Forks: 3.8K forks

💻 Programming Languages: Python - Dockerfile

🏷️ Related Topics:

#python #pdf #parser #ocr #pdf_converter #extract_data #document_analysis #pdf_parser #layout_analysis #ai4science #pdf_extractor_rag #pdf_extractor_llm #pdf_extractor_pretrain

==================================
🧠 By: https://t.me/DataScienceM