#document
3 Entdeckungen · Handverlesene Entdeckungen aus dem offenen Web, neueste zuerst.
-
Show HN: Document parsing 5B tokens on a single CPU thread
mit license: https://github.com/john-friedman/doc2struct doc2struct 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
Show HN · EN
-
Dharma Field Extractor: Any Document In, Structured Fields in JSON Out
A Blog post by Dharma-AI on Hugging Face
Hugging Face Blog · EN
-
Document Picture-in-Picture API与任意元素画中画实现
好消息，之前只有视频元素才能画中画，现在任意元素都能独立成画中画窗口了，小屏摸鱼有了新选择。
张鑫旭-鑫空间-鑫生活 · ZH