Full-stack developer, passionate about AI and learning new things. Powered by coffee and curiosity. Full-stack developer, passionate about AI and learning new things. Powered by coffee and curiosity.

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Pure TypeScript, cross-platform module for extracting text, images, and tabular data from PDFs. Run 🤗 directly in your browser or in Node!

Argonne National Laboratory today announced a PDF parser that the lab said could speed up the creation of AI systems trained on scientific literature, leading to better AI research assistants, ...

Abstract: This paper describes the Verifiable Automatic Language Analysis and Recognition for Inputs (VALARIN) system to process, evaluate, and flag unsafe PDFs. The ...

HTMX is a newer technology that takes plain old HTML and gives it extra powers like Ajax and DOM swaps. It’s included in my personal list of good ideas because it eliminates a whole realm of ...

Chemists achieve synthetic feat with radioactive promethium for the first time. “It’s a tour de force,” says Polly Arnold, a chemist at Lawrence Berkeley National Laboratory in Berkeley, California, ...

Abstract: A programmable packet parser with online configuration, which can identify protocols and extract key fields on demand at runtime, is essential to realize protocol upgrading for satellite ...