shell-gpt 0.8.6

A command-line productivity tool powered by ChatGPT, will help you accomplish your tasks faster and more efficiently.

Shell GPT

A command-line productivity tool powered by OpenAI's GPT-3.5 model. As developers, we can leverage ChatGPT capabilities to generate shell commands, code snippets, comments, and documentation, among other things. Forget about cheat sheets and notes, with this tool you can get accurate answers right in your terminal, and you'll probably find yourself reducing your daily Google searches, saving you valuable time and effort.

Installation

pip install shell-gpt==0.8.6

You'll need an OpenAI API key, you can generate one here.

If the$OPENAI_API_KEY environment variable is set it will be used, otherwise, you will be prompted for your key which will then be stored in ~/.config/shell_gpt/.sgptrc.

Usage

sgpt has a variety of use cases, including simple queries, shell queries, and code queries.

Simple queries

We can use it as normal search engine, asking about anything:

sgpt "nginx default config file location"
# -> The default configuration file for Nginx is located at /etc/nginx/nginx.conf.

sgpt "docker show all local images"
# -> You can view all locally available Docker images by running: `docker images`

sgpt "mass of sun"
# -> = 1.99 × 10^30 kg

Conversion

Convert various units and measurements without having to search for the conversion formula or use a separate conversion website. You can convert units such as time, distance, weight, temperature, and more.

sgpt "1 hour and 30 minutes to seconds"
# -> 5,400 seconds

sgpt "1 kilometer to miles"
# -> 1 kilometer is equal to 0.62137 miles.

Shell commands

Have you ever found yourself forgetting common shell commands, such as chmod, and needing to look up the syntax online? With --shell or shortcut -s option, you can quickly find and execute the commands you need right in the terminal.

sgpt --shell "make all files in current directory read only"
# -> chmod 444 *
# -> Execute shell command? [y/N]: y
# ...

Shell GPT is aware of OS and $SHELL you are using, it will provide shell command for specific system you have. For instance, if you ask sgpt to update your system, it will return a command based on your OS. Here's an example using macOS:

sgpt -s "update my system"
# -> sudo softwareupdate -i -a

The same prompt, when used on Ubuntu, will generate a different suggestion:

sgpt -s "update my system"
# -> sudo apt update && sudo apt upgrade -y

Let's try some docker containers:

sgpt -s "start nginx using docker, forward 443 and 80 port, mount current folder with index.html"
# -> docker run -d -p 443:443 -p 80:80 -v $(pwd):/usr/share/nginx/html nginx
# -> Execute shell command? [y/N]: y
# ...

Also, we can provide some parameters name in our prompt, for example, passing output file name to ffmpeg:

sgpt -s "slow down video twice using ffmpeg, input video name \"input.mp4\" output video name \"output.mp4\""
# -> ffmpeg -i input.mp4 -filter:v "setpts=2.0*PTS" output.mp4
# -> Execute shell command? [y/N]: y
# ...

We can apply additional shell magic in our prompt, in this example passing file names to ffmpeg:

ls
# -> 1.mp4 2.mp4 3.mp4
sgpt -s "using ffmpeg combine multiple videos into one without audio. Video file names: $(ls -m)"
# -> ffmpeg -i 1.mp4 -i 2.mp4 -i 3.mp4 -filter_complex "[0:v] [1:v] [2:v] concat=n=3:v=1 [v]" -map "[v]" out.mp4
# -> Execute shell command? [y/N]: y
# ...

Since ChatGPT can also do summarization and analyzing of input text, we can ask it to generate commit message:

sgpt "Generate git commit message, my changes: $(git diff)"
# -> Commit message: Implement Model enum and get_edited_prompt() func, add temperature, top_p and editor args for OpenAI request.

Or ask it to find error in logs and provide more details:

sgpt "check these logs, find errors, and explain what the error is about: ${docker logs -n 20 container_name}"
# ...

Generating code

With --code parameters we can query only code as output, for example:

sgpt --code "Solve classic fizz buzz problem using Python"

for i in range(1, 101):
    if i % 3 == 0 and i % 5 == 0:
        print("FizzBuzz")
    elif i % 3 == 0:
        print("Fizz")
    elif i % 5 == 0:
        print("Buzz")
    else:
        print(i)

Since it is valid python code, we can redirect the output to file:

sgpt --code "solve classic fizz buzz problem using Python" > fizz_buzz.py
python fizz_buzz.py
# 1
# 2
# Fizz
# 4
# Buzz
# Fizz
# ...

Chat

To start a chat session, use the --chat option followed by a unique session name and a prompt. You can also use "temp" as a session name to start a temporary chat session.

sgpt --chat number "please remember my favorite number: 4"
# -> I will remember that your favorite number is 4.
sgpt --chat number "what would be my favorite number + 4?"
# -> Your favorite number is 4, so if we add 4 to it, the result would be 8.

You can also use chat sessions to iteratively improve ChatGPT's suggestions by providing additional clues.

sgpt --chat python_requst --code "make an example request to localhost using Python"

import requests

response = requests.get('http://localhost')
print(response.text)

Asking ChatGPT to add a cache to our request.

sgpt --chat python_request --code "add caching"

import requests
from cachecontrol import CacheControl

sess = requests.session()
cached_sess = CacheControl(sess)

response = cached_sess.get('http://localhost')
print(response.text)

We can use --code or --shell options to initiate --chat, so you can keep refining the results:

sgpt --chat sh --shell "What are the files in this directory?"
# -> ls
sgpt --chat sh "Sort them by name"
# -> ls | sort
sgpt --chat sh "Concatenate them using FFMPEG"
# -> ffmpeg -i "concat:$(ls | sort | tr '\n' '|')" -codec copy output.mp4
sgpt --chat sh "Convert the resulting file into an MP3"
# -> ffmpeg -i output.mp4 -vn -acodec libmp3lame -ac 2 -ab 160k -ar 48000 final_output.mp3

REPL

There is very handy REPL (read–eval–print loop) mode, which allows you to interactively chat with GPT models. To start a chat session in REPL mode, use the --repl option followed by a unique session name. You can also use "temp" as a session name to start a temporary REPL session. Note that --chat and --repl are using same chat sessions, so you can use --chat to start a chat session and then use --repl to continue the conversation in REPL mode. REPL mode will also show history of your conversation in the beginning.

sgpt --repl temp
Entering REPL mode, press Ctrl+C to exit.
>>> What is REPL?
REPL stands for Read-Eval-Print Loop. It is a programming environment ...
>>> How can I use Python with REPL?
To use Python with REPL, you can simply open a terminal or command prompt ...

REPL mode can work with --shell and --code options, which makes it very handy for interactive shell commands and code generation:

sgpt --repl temp --shell
Entering shell REPL mode, type [e] to execute commands or press Ctrl+C to exit.
>>> What is in current folder?
ls
>>> Show file sizes
ls -lh
>>> Sort them by file sizes
ls -lhS
>>> e (enter just e to execute commands)
...

Example of using REPL mode to generate code:

sgpt --repl temp --code
Entering REPL mode, press Ctrl+C to exit.
>>> Using Python request localhost:80
import requests
response = requests.get('http://localhost:80')
print(response.text)
>>> Change port to 443
import requests
response = requests.get('https://localhost:443')
print(response.text)

Chat sessions

To list all the current chat sessions, use the --list-chat option:

sgpt --list-chat
# .../shell_gpt/chat_cache/number
# .../shell_gpt/chat_cache/python_request

To show all the messages related to a specific chat session, use the --show-chat option followed by the session name:

sgpt --show-chat number
# user: please remember my favorite number: 4
# assistant: I will remember that your favorite number is 4.
# user: what would be my favorite number + 4?
# assistant: Your favorite number is 4, so if we add 4 to it, the result would be 8.

Request cache

Control cache using --cache (default) and --no-cache options. This caching applies for all sgpt requests to OpenAI API:

sgpt "what are the colors of a rainbow"
# -> The colors of a rainbow are red, orange, yellow, green, blue, indigo, and violet.

Next time, same exact query will get results from local cache instantly. Note that sgpt "what are the colors of a rainbow" --temperature 0.5 will make a new request, since we didn't provide --temperature (same applies to --top-probability) on previous request.

This is just some examples of what we can do using ChatGPT model, I'm sure you will find it useful for your specific use cases.

Runtime configuration file

You can setup some parameters in runtime configuration file ~/.config/shell_gpt/.sgptrc:

# API key, also it is possible to define OPENAI_API_KEY env.
OPENAI_API_KEY=your_api_key
# OpenAI host, useful if you would like to use proxy.
OPENAI_API_HOST=https://api.openai.com
# Max amount of cached message per chat session.
CHAT_CACHE_LENGTH=100
# Chat cache folder.
CHAT_CACHE_PATH=/tmp/shell_gpt/chat_cache
# Request cache length (amount).
CACHE_LENGTH=100
# Request cache folder.
CACHE_PATH=/tmp/shell_gpt/cache
# Request timeout in seconds.
REQUEST_TIMEOUT=60
# Default OpenAI model to use.
DEFAULT_MODEL=gpt-3.5-turbo

Full list of arguments

╭─ Arguments ────────────────────────────────────────────────────────────────────────────────────────────────╮
│   prompt      [PROMPT]  The prompt to generate completions for.                                            │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭─ Options ──────────────────────────────────────────────────────────────────────────────────────────────────╮
│ --model            [gpt-3.5-turbo|gpt-4|gpt-4-32k]  OpenAI GPT model to use. [default: gpt-3.5-turbo]      │
│ --temperature      FLOAT RANGE [0.0<=x<=1.0]        Randomness of generated output. [default: 0.1]         │
│ --top-probability  FLOAT RANGE [0.1<=x<=1.0]        Limits highest probable tokens (words). [default: 1.0] │
│ --editor                                            Open $EDITOR to provide a prompt. [default: no-editor] │
│ --cache                                             Cache completion results. [default: cache]             │
│ --help                                              Show this message and exit.                            │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭─ Assistance Options ───────────────────────────────────────────────────────────────────────────────────────╮
│ --shell  -s                 Generate and execute shell commands.                                           │
│ --code       --no-code      Generate only code. [default: no-code]                                         │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭─ Chat Options ─────────────────────────────────────────────────────────────────────────────────────────────╮
│ --chat        TEXT  Follow conversation with id, use "temp" for quick session. [default: None]             │
│ --repl        TEXT  Start a REPL (Read–eval–print loop) session. [default: None]                           │
│ --show-chat   TEXT  Show all messages from provided chat id. [default: None]                               │
│ --list-chat         List all existing chat ids. [default: no-list-chat]                                    │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Docker

Run the container using the OPENAI_API_KEY environment variable, and a docker volume to store cache:

docker run --rm \
           --env OPENAI_API_KEY="your OPENAI API key" \
           --volume gpt-cache:/tmp/shell_gpt \
       ghcr.io/ther1d/shell_gpt --chat rainbow "what are the colors of a rainbow"

Example of a conversation, using an alias and the OPENAI_API_KEY environment variable:

alias sgpt="docker run --rm --env OPENAI_API_KEY --volume gpt-cache:/tmp/shell_gpt ghcr.io/ther1d/shell_gpt"
export OPENAI_API_KEY="your OPENAI API key"
sgpt --chat rainbow "what are the colors of a rainbow"
sgpt --chat rainbow "inverse the list of your last answer"
sgpt --chat rainbow "translate your last answer in french"

You also can use the provided Dockerfile to build your own image:

docker build -t sgpt .