I spun up ollama and paperless-gpt to add ai ocr sidecar to paperless-ngx. It's okay. It can read handwritten stuff okayish, which is better than tesseract (doesnt read hand writing at all), so I throw handwritten stuff to it, but the difference on typed text is marginal in my single day I spent testing 3 different models on a few different typed receipts.
couch1potato
joined 1 year ago
If i remember correctly, jackett allows you to add trackers that prowlarr doesn't have natively. Then you add jackett to prowlarr to distribute to the rest of your containers.
I mean, this take makes as much sense as France asking for the statue back
I tried posteo and eclipso before settling on mailbox.org.
Coming from gmail.
Set up a potato phone camera on a tripod to record the screen 😂
If you search around there are several libraries you can join from afar without proving local residency. I had like 5 libraries from around the US on libby while the free downloading was still viable.
Elsa impregnation videos, you say. Huh. Hmm.
I tried minicpm-v, granite3.2-vision, and mistral.
Granite didn't work with paperless-gpt at all. Mistral worked sometimes but also just kept running sometimes and didn't finish within a reasonable time (15 minutes for 2 pages). minicpm-v finishes every time, but i just looked at some of the results and seems as though it's not even worth keeping it running either. I suppose maybe the first one I tried that gave me a good impression was a fluke.
To be fair, I'm a noob at local ai, and I also don't have a good gpu (gtx1650). So these failures could all be self induced. I like the idea of ai powered ocr so I'll probably try again in the future...