Cipri
-
Posts
29 -
Joined
-
Last visited
Reputation Activity
-
Cipri reacted to vitor in Why Some Apps Can Access the Email.app While Alfred Can't
It is possible to make a workflow for it, Mail has an AppleScript dictionary. The Mail Link workflow uses it. The reason there isn’t a workflow for it is more likely to be that Alfred can already send emails by default and that looks to be enough for what most people want. Whatever information you saw about Alfred being unable to do it might have referred to some specific feature of Mail which is not automatable. Apple has stopped adding AppleScript capabilities to their apps (even before making Shortcuts) even as it adds more features.
Here’s a first proof of concept. I can already:
Show messages from inbox. Open a message in the Mail app. Open a reply to a message ⇧↩. Delete a message ⌘↩. Toggle read status ⌥↩. Might work this into a more full fledged workflow soon.
-
Cipri reacted to Aviv in Engage with your contacts in a lot of apps
Open the Alfred workflow page Go to the workflow you'd like to debug Click the little `Debugger Stopped` Play button A new debug screen would pop up Use the workflow, place all output logs of the debugger in here
You can find more information in here ✨
-
Cipri reacted to zeitlings in Calendar++
I'll look into it. I've also noticed that these cases need even more attention to be handled elegantly.
Thanks! I have looked into this in the past, and if memory serves, there is an extra layer of complexity since the calendars that provide the holiday events are usually added by subscribing to them. I've put it back on the roadmap to revisit the matter.
-
Cipri reacted to _oho in Using alternative and local models with the ChatGPT / DALL-E workflow
Actually, you can use Ollama (https://github.com/ollama/ollama) to serve locally any available open source models (including gemma from Google, llama2 from Meta, or Mistral from the French startup, but many others ...).
Ollama is compatible with OpenAI API so I just hacked a bit the current workflow by changing `chatgpt_api_enpoint` to `http://localhost:11434`
+ changing model name and label in `userconfigurationconfig`
And to my great surprise it works ...
Of course, I believe your mac should be robust enough. Forget to mention I have a M3 Max with 48 Go of RAM. But I'm pretty sure it's reasonably work on a M1 with 8 Mo of RAM. On my M3 answer is very fast.
It would be good to have an update of the workflow that would add the option (+ howto) to use Ollama...
_oho.
-
Cipri got a reaction from karutt in QuickTimer: Control Clock.app Timers Directly from Alfred
It would be nice if it were possible to give the timer a name and when it finished the warning would appear in large text on the screen.
-
Cipri reacted to Vero in Web Search Suggest
@Cipri You may want to post the issue to the workflow creator's own Github as they may have suggestions for you:
https://github.com/zqzten/alfred-web-search-suggest
-
Cipri got a reaction from vitor in Installing formulae error
It worked after installing with the command. Thank you very much for your help!