[HELP NEEDED] add vision support / multimodal image input#430
[HELP NEEDED] add vision support / multimodal image input#430thiswillbeyourgithub wants to merge 1 commit intojackMort:mainfrom
Conversation
Signed-off-by: thiswillbeyourgithub <26625900+thiswillbeyourgithub@users.noreply.github.com>
|
So after further testing I know this works and even included a way to directly paste images into chatgpt.nvim using Here's the full diff : Edit: improved it some more: With the following shortcut: |
|
Edit: a sure way but less privacy friendly to send image is to first send it to litterbox: -- upload to litterbox then send as url
local handle = io.popen('curl -F "reqtype=fileupload" -F "time=1h" -F "fileToUpload=@' .. line .. '" https://litterbox.catbox.moe/resources/internals/api.php')
local result = handle:read("*a")
handle:close()
return { type = "image_url", image_url = { url = result} }
|
|
Update: although the way to send images via the shortcut can be sound, i mainly made this PR to allow others to easily give it a try.
In any way I won't do any enhancement until someone fixed the curl to send files :/ I can put this in draft if you want but I woumd prefer the extra visibility of staing Open |


Signed-off-by: thiswillbeyourgithub 26625900+thiswillbeyourgithub@users.noreply.github.com
Fixed #429