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

Chunking large copies #983

Open
2 tasks done
daxmc99 opened this issue Dec 10, 2024 · 2 comments
Open
2 tasks done

Chunking large copies #983

daxmc99 opened this issue Dec 10, 2024 · 2 comments
Labels
enhancement New feature or request

Comments

@daxmc99
Copy link

daxmc99 commented Dec 10, 2024

Before Submitting Your Feature Request

  • Check that there isn't already a similar feature request to avoid creating a duplicate.
  • I have seen the FAQ.

Problem

When pasting large amounts of text into an LLM you might need to chunk the input to get around context window limitations or web-app limitations.

Tools like https://chatgpt-prompt-splitter.vercel.app/ split a large copy into multiple pieces and allow for easily pasting chunks into an LLM.

Solution

Maccy should support a workflow or option to chunk inputs that exceed some custom token size.

@daxmc99 daxmc99 added the enhancement New feature or request label Dec 10, 2024
@p0deje
Copy link
Owner

p0deje commented Dec 10, 2024

Can you elaborate what the workflow in Maccy would look like?

@bigplayer-ai
Copy link

I’m not sure if this is what the original poster meant, but I find it frustrating that Mac cannot handle saving or copying large amounts of text, such as 300,000 to 400,000 characters. For example, try copying the content of this text file:
https://www.damienelliott.com/wp-content/uploads/2020/07/Lorem-ipsum-dolor-sit-amet.txt

With the introduction of large language models capable of processing such extensive context, it would be amazing if Mac’s clipboard manager could support this volume of text in a single copied item.

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

No branches or pull requests

3 participants