Are you using this tool in your workflow? We’d love to learn more about your experience. Sharing your use case helps us improve the service for everyone. This project provides a powerful and flexible ...

Open-source OCR from Baidu eliminates the GPU memory wall that limits long-document parsing. Unlimited OCR uses a constant KV ...

Mistral AI's OCR 4 delivers structured document intelligence with bounding boxes, confidence scores, and self-hosted ...

UC Berkeley's PixelRAG renders pages as screenshots instead of parsing text, boosting RAG accuracy by up to 18.1% and cutting AI agent token costs 10x.

This package contains tools for parsing source code into annotated json data structure: we extracted import statements, global assignments, top-level methods, classes, class methods and attributes, ...