Standard RAG pipelines treat documents as flat strings of text. They use "fixed-size chunking" (cutting a document every 500 characters). This works for prose, but it destroys the logic of technical ...

Abstract: Optical character recognition (OCR) in industrial environments often struggles with degraded text, such as handwriting or text obscured by complex backgrounds. Traditional methods address ...

Recent advancements in multimodal slow-thinking systems have demonstrated remarkable performance across diverse visual reasoning tasks. However, their capabilities in text-rich image reasoning tasks ...

This is just a fun project, to be able to analyze all data log entries from the game The Last Caretaker, and chat about it with an LLM. At first, I wasn't really interested in the story of the game, ...