Command to Selected Finder Object
under review
A
Adam Ram
It would be very handy when I select a text files or images on Finder. Just launch a Command to process that file.
This will turn those 2-3 steps into only 1 step. This will save a lot of time. No need to open Word/PDF to get the texts, or open Preview to open image and take an Image Analysis with screenshot.
It's like when I have a bunch of pdf/txt/doc, I can directly summarize it right from Finder.
Please don't limit vision model to only external LLM, since some people run locally Qwen2-VL with vision capable.
Daniel Nguyen
under review
Hmmm you can already do this. Right-click on the file, select "Open With" > "BoltAI".
A
Adam Ram
Daniel Nguyen It's different approach I think. This is a good example, when I have a Command that enable ffmpeg plugin, it can directly convert MP4 video to MP3.
Thank's to Bolt's ffmpeg plugin feature. This is really handy. With only a Command I can convert a video to MP3. It will be more powerful if we can get various Command to process certain file on Finder.
What you mean with "Open With", we should prompt it again. But with Command, it can be automatically processed with predefined system prompt. Also "Open With" is not working with MP4 files to BoltAI.
Daniel Nguyen
Adam Ram Have you try it? Here is the release note https://boltai.com/changelog/v1210-new-command/66ec31eb1516dbe48655a608
Is this what you're looking for?
A
Adam Ram
Daniel Nguyen Thank's that feature is handy. But when I select a image file like png/jpg, Bolt behaviour is only read the file name, not the content.
It is working for video/audio files with ffmpeg plugin. Is there any same way to process image files? Howto make a plugins read the file and passthrough to model so that Instant Command will work also to any image files?