Comment by Kirby64
12 hours ago
> I have an older M2 Mac mini that does the OCR and visual description of all my screenshots. Screenshots are stored on my NAS.
Doesn't Apple do this already within it's OS all locally? It certainly does it for OCR and categorization.
EDIT: Also, no reason to use a generic LLM for this. This functionality exists in something like Immich (both OCR and 'context categorization'), and doesn't tie you into the Apple ecosystem either.
I personally use Apple Photos for this. It stores the original, plus makes them nicely searchable, so I have a Hazel action that takes screenshots from the desktop (and from my NAS where mobile devices back them up) and imports them.
Works out really well.
The standard system search will also search for text in images now. I think at first it was Photos only, but now its system wide.