get chatGPT to help you generate shell commands directly from your CLI

Example usage: ai "list all python files in my current directory"

Required Installations:

• sudo apt install python or brew install python (tested on 3.10.10)
• pip install openai

Optional:

• sudo apt install xclip

1. go to https://platform.openai.com/account/api-keys and generate an API key
2. create a file called .openai-key and place it in a folder called keys the root directory of the project. i.e keys/.openai-key

Note: You may need to provide your billing details for the openAI API to allow your requests. You can set a maximum dollar spend amount limit to something you can live with. 😄💸

Modify the constants found at the top of main.py file to your specific needs.

# keys folder in the root of the project with the api key in a file named `.openai-key`
API_KEY_LOCATION = Path("keys") / ".openai-key"
OS_VERSION = "ubuntu 20.04 running on wsl2"
SHELL_TYPE = "bash"

TODO: update docs with powershell and env variable update

1. Add the snippet below to your ~./.bashrc file and update the path to your python script location mine is ~/.my_toolbox/chatgpt-cli-helper/src/main.py

function ai() {
    local ai_cmd=$(python ~/.my_toolbox/chatgpt-cli-helper/src/main.py "$1")
    echo "$ai_cmd"            # print the selected command
    echo "$ai_cmd" | clip.exe # add to clipboard in wsl2
    # optionally
    # printf "%s" "$ai_cmd" | xclip -selection clipboard # copy the command to
    # clipboard on non wsl linux os
    # printf "\033[G\033[K%s" "$ai_cmd" # place the command on the command line buffer
}

IMPORTANT:
Remember to relaunch your shell for changes to take effect or do source ~/.bashrc