Open Oobert opened 5 months ago
I might have to look up if it's possible for a logseq plugin to access files on the client PC as this may be a security issue if I can casually have access to your files, if it's possible I guess it's possible to support feeding those images to a vision model via https://ollama.com/library/llava. will check it out and implement it if possible
Would it be possible to feed an image from logseq to ollama and have it do OCR or summarize it? I take a lot of screenshots during meetings and it would be great to have the text on the images or the images them self summarized so that the information would become searchable.
I don't know what is possible with Logseq plugins yet as I just started using Logseq last week.
Thanks for creating the plugin. I can't wait to get it setup and try it out.