Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

some confusing buttons and kind proposals [mac OS ] #116

Open
WYang555 opened this issue Feb 1, 2025 · 2 comments
Open

some confusing buttons and kind proposals [mac OS ] #116

WYang555 opened this issue Feb 1, 2025 · 2 comments

Comments

@WYang555
Copy link

WYang555 commented Feb 1, 2025

The text generated by the LLM sometimes appears in the current note (e.g., MS, Word document) and sometimes in a new window, making it difficult to anticipate. I hope the developers can address this puzzlement. I do not have a better suggestion yet ( is it possible to create a code snippet that identifies the file type, such as a word document, PDF, HTML, or others, before processing the text....ok! it just a hypothesis).

if the app can support iCloud LLMs, it would be better. It would be awesome if we could let people experience better LLMs that they've set up themselves. Sometimes, the devices people are using just aren't powerful enough to run the really big models, so this would be a great solution!

hope this app can be the best one !

@Joaov41
Copy link

Joaov41 commented Feb 1, 2025

If you are in a text input view, it should show there or replace if you have text selected; if not, the pop-up window shows up.

@theJayTea
Copy link
Owner

theJayTea commented Feb 3, 2025

Hello @WYang555 , thanks for reaching out.

To clarify the intuition behind the buttons:
The Proofread, Rewrite, Friendly, Concise, and Professional options replace text you select.

Only the options where you want to select & understand other text (Summary, Key Points, Table) open in a separate window so you can chat with the response & have it rendered in Markdown.

Also, Writing Tools supports cloud-based LLMs if that’s what you meant - there’s support for providers such as Gemini, OpenAI, and Mixtral in Settings.

@Aryamirsepasi is also adding support for built-in local LLMs (without having to download Ollama etc.).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants