Re:Show HN: Kreuzberg – Modern async Python library for docu...
by skavi on Saturday February 15, 2025 @09:54PM
(#43064874)
in that case, what’s the deal with extract_bytes being async? i’m not incredibly familiar with python, but i’d expect a “byte string” to be in memory.
[ Parent
| on HN ]
Re:Show HN: Kreuzberg – Modern async Python library for docu...
by nhirschfeld on Sunday February 16, 2025 @02:41AM
(#43066164)
You still need to write it to file to process it via pandoc/tesseract etc.
There are alternative options to tesseract ofc.