Comments (3)
@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.
from shellgpt.
@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.
from shellgpt.
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?
from shellgpt.
Related Issues (20)
- Keep getting an error even when changing the model to gpt-3.5-turbo HOT 5
- Error 'gpt-4' does not exist - MacOS HOT 6
- Features suggestion HOT 5
- Support other models (like GPT4All) HOT 1
- API key not detected using Fish shell HOT 2
- Can't have line breaks in pasted input HOT 1
- Install script, `--repl` issues on Windows HOT 5
- howto gpt-4-32k ? HOT 1
- Higher level refactoring w/ many files HOT 10
- Add local model HOT 1
- Error when installing HOT 3
- Allow to set a custom OpenAI endpoint URL HOT 3
- Request: way to pass an image HOT 2
- System already had the same command? HOT 6
- gpt --config keeps prompting to update to newer version, even after updating HOT 2
- Request: be able to paste long pieces of text in repl mode HOT 3
- After updating to latest 0.3.8, gpt command doesn't return any response HOT 6
- Handle insufficient_quota error HOT 3
- Feature request: Able to log the answers of the gpt commands HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from shellgpt.