configure removal of wpm limitation

[ekg]

configure removal of wpm limitation

[mattvr]

@ekg I've added the ability to bypass the WPM buffered output:

• You can now pass a --wpm value less than 0 (e.g. --wpm=-1). This will bypass the buffer and output as fast as possible.
• You can also configure this permanently by manually editing your $HOME/.gpt/config.json and adding a line for "wpm": -1

Relevant release notes and update instructions are here: https://github.com/mattvr/ShellGPT/releases/tag/0.3.1

Thanks for the feedback and let me know if you have any issues or further suggestions.

[mattvr]

@ekg the purpose is to make the output appear smooth. Most GPT tools have choppy output that comes in chunks of words. I found that aesthetically less pleasing than character-by-character streaming.

You could alias gpt to gpt --wpm 9999 $@ in your shell's profile to avoid the throttling. I could also add a permanent config setting for it in the next update.

[ekg]

Thanks, I understand that. From my perspective these interfaces are useful in an environment that is unlikely to be observed by a human, so simulating human behavior is irrelevant. I can do the alias of course. Does setting the wpm value to a huge number ensure the flow is as fast as possible?