Skip to content

Instantly share code, notes, and snippets.

@Talor-A
Last active November 3, 2024 21:24
Show Gist options
  • Save Talor-A/f1a8e487025187995049870b6d62db70 to your computer and use it in GitHub Desktop.
Save Talor-A/f1a8e487025187995049870b6d62db70 to your computer and use it in GitHub Desktop.
on open dropped_items
repeat with imageFile in dropped_items
set imagePath to POSIX path of imageFile
try
set cmd to "PATH=$PATH:~/.local/bin && llm prompt \"You are a helpful image transcriber bot and it is your job to explain exactly what is in images so that blind people and other LLMs can understand the image. first state in plain terms what the pictured image looks like. then exactly transcribe word-for-word all text inside. it is important to transcribe all content so that no detail is omitted. do not include any other text in your reply besides these two things. EXAMPLE: 'a chat app with the message hello world as the first reply'. Now give your description of this image:\" -a " & quoted form of imagePath
set altText to do shell script cmd
display dialog altText buttons {"Copy", "OK"} default button "Copy"
if button returned of result is "Copy" then
set the clipboard to altText
end if
on error errMsg
display dialog "Error processing image: " & errMsg buttons {"OK"} default button "OK" with icon stop
end try
end repeat
end open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment