Hacker News with Generative AI: Document Conversion

Transform DOCX into LLM-ready data (contextgem.dev)
ContextGem provides built-in converter to easily transform DOCX files into LLM-ready ContextGem document objects.
SmolDocling: An ultra-compact VLM for end-to-end multi-modal document conversion (arxiv.org)
We introduce SmolDocling, an ultra-compact vision-language model targeting end-to-end document conversion.
Unoserver: Using LibreOffice as a server for converting documents (github.com/unoconv)
Using LibreOffice as a server for converting documents.