mit license: https://github.com/john-friedman/doc2structdoc2struct is an algorithm that can parse documents fast on one thread. For example it can parse every every 2025 annual report 19GB in 40s.It preserves nesting, does mild table cleaning, among other things.It succeeds my earlier document parser https://github.com/john-friedman/doc2dict
Comments URL: https://news.ycombinator.com/item?id=50388374
Points: 1
# Comments: 0
The Document Foundation, the non-profit steering the development of LibreOffice, has unveiled a new logo. The change means that, for the first time since its inception…
I made my laptop generate 220,202 AI tokens in about 13 minutes because I wanted to answer a question. Then I started wondering what would happen if I did it again. And…
Article URL: https://www.nace.ai/blog/document-intelligence-launch Comments URL: https://news.ycombinator.com/item?id=50016677 Points: 1 # Comments: 0
Discussion (0)
No comments yet. Start the conversation!