datalab-to/chandra 2: OCR Model for Complex Documents Reaches 8K Stars (+2,928/Week)
GitHub·medium signal
Chandra 2, released in March 2026, converts images and PDFs to HTML/Markdown/JSON while preserving layout — handling math equations, handwritten text, form checkboxes, complex tables, and 90+ languages. Runs locally via HuggingFace or vLLM for production. Apache 2.0 code license. The +2,928 stars/week velocity suggests strong demand for document-to-LLM pipelines beyond simple OCR.