mountaineerbr

This is a terrible approach. The Ollama project members seem to use MacOS which is a bad platform by defaults. Keep in mind, MacOS uses launchd, which inspired the creation...

We use `bat` to render markdown in our [shell warper](https://github.com/mountaineerbr/shellChatGPT). It can also be configured for bat to use the "latex" language renderer. You may want to try it: `chatgpt.sh...

While this is not implemented here, you may want to try my [`chatgpt.sh` shell script](https://github.com/mountaineerbr/shellChatGPT) which supports _dall-e-3_ model for image generations by defaults.

Hopefully, invalid options will be silently ignored by the server.

Outcome will be random. You may try it yourself to even know what differences may arise. What we do in my OpenAI (and Ollama) API warping is, leave images the...

The first input prompt can be a file path, so it will be read. No?

Well, did you check the big prompt option? ``` -b, --big-prompt Allow multi-line prompts during chat mode ``` It can be improved, of course. Instead of using the cat command,...

You may try to install `glow`. It seems you haven't got `glow`, so I reckon the problem is with `echo -e` in [line 450](https://github.com/0xacx/chatGPT-shell-cli/blob/926587a2234b8ae3754a1db9715f4636205159dc/chatgpt.sh#L450). OBS: I am not sure how...

I guess prompting engineering is changing so fast (and models being censored), that anything more than simple will make it hard to maintain with following OpenAI models.. Also, if you...

I have something that may help in [`my .bashrc`](https://gitlab.com/mountaineerbr/dotfiles/-/blob/main/.rc): ```#jq filters #get all paths of a json jqpath() { jq -r 'def path2text($value): def tos: if type == "number" then...