Skip to main content

A smart terminal assistant that helps you find the right command

Project description

PyPI version

Terminal-copilot

Are you tired of Googling basic terminal commands every time you forget the syntax? Look no further! terminal-copilot is here to help.

With terminal-copilot, you can quickly and easily access commonly used terminal commands right from the command line. Simply type copilot followed by your desired command in natural language and let terminal-copilot do the rest.

For example, if you want to find a file ending in .txt, simply type: copilot find a file ending in .txt terminal-copilot will then display the correct syntax for the command you need: find . -name "*.txt" With options to execute, copy, or explain the proposed terminal command.

You can also use the copilot to ask a general question to gpt4 from your command line using the -q option copilot -q "What is the best drink for late night coding?"

Installation

To use terminal-copilot, you must first install it on your system. The easiest way to do this is using pip: pip install terminal-copilot Once terminal-copilot is installed, you can access it from the command line by typing copilot followed by your question.

Example Usage

terminal-copilot is designed to be simple and intuitive to use. Simply type copilot followed by your question and terminal-copilot will display the correct syntax for the command you need.

Here are some examples of how you can use terminal-copilot:

  1. copilot list the compute instances in gcloud
  2. copilot find all mp3 files in my home directory
  3. copilot install the openai package for python
  4. copilot clean up my docker images

or you can ask a general question to gpt4 from your command line using the -q option copilot -q Why is 42 the meaning of life (note that question marks are not supported atm..)

Arguments

Terminal-copilot can be called with optional command line arguments:

  • -a, --alias: Enables the inclusion of aliases in the prompt sent to the OpenAI API. May potentially send sensitive information to OpenAI.
  • -v, --verbose: Increases output verbosity of the tool.
  • -g, --git: This flag enables the inclusion of Git context in the prompt sent to the OpenAI API. This can be useful for users working with Git repositories and may include the current branch name, repository status, recent commit messages, and file history.
  • -hist, --history: Enables the inclusion of terminal history in the prompt sent to the OpenAI API. May potentially send sensitive information to OpenAI and increase the number of tokens used.
  • -j, --json: Output data as JSON instead of using an interactive prompt.
  • -c, --count: The number of commands to output when JSON output is specified.
  • -m, --model: The model to use. Defaults to gpt-3.5-turbo.
  • -ns, --no-stream: Disable streaming the command into the terminal (by default, streaming is enabled).

Requirements

Python 3.7+ Mac Os, Windows, or Linux

Sensitive Information

Please note that terminal-copilot has the ability to send sensitive information to OpenAI as part of the prompt used to generate terminal commands. This includes the --alias,--history, --git command line arguments, which may include sensitive information such as aliases and terminal history. If you are concerned about the potential for sensitive information to be sent to OpenAI, we recommend not using these flags. We recommend that users exercise caution when using these optional features and consider the potential risks before enabling them.

Development

Contributing

We welcome contributions to terminal-copilot! If you have an idea for a new feature or have found a bug, please open an issue. If you would like to contribute code, please open a pull request!

Thank you for considering contributing to terminal-copilot! Together, we can make it an even better tool for accessing terminal commands.

Local Installation

  1. Clone the repo
  2. python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt
  3. python setup.py install

Packaging for PyPi

First make sure you have pip install wheel and pip install twine installed. Then run the following commands: 0. Modify version in setup.py

  1. rm -rf dist
  2. python setup.py sdist bdist_wheel
  3. twine upload dist/*

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

terminal-copilot-1.5.3.tar.gz (18.8 kB view details)

Uploaded Source

Built Distribution

terminal_copilot-1.5.3-py3-none-any.whl (20.9 kB view details)

Uploaded Python 3

File details

Details for the file terminal-copilot-1.5.3.tar.gz.

File metadata

  • Download URL: terminal-copilot-1.5.3.tar.gz
  • Upload date:
  • Size: 18.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.6

File hashes

Hashes for terminal-copilot-1.5.3.tar.gz
Algorithm Hash digest
SHA256 0f71090559dc30653c9c31dc20cbfdb251747756a422b1511b9b1e78337fa200
MD5 19984f88cb243372ff69b7d4aa8740b1
BLAKE2b-256 5baf476aeb0658d0164ae440d480736b793155c31a650a31cf620e1c5159050f

See more details on using hashes here.

File details

Details for the file terminal_copilot-1.5.3-py3-none-any.whl.

File metadata

File hashes

Hashes for terminal_copilot-1.5.3-py3-none-any.whl
Algorithm Hash digest
SHA256 655ec639922068f112e67b56c1568858643ca9783b036518d8df107219a61d69
MD5 b7a7e3d97bac245c0b81985ccbfa2d57
BLAKE2b-256 6d8e4ae3f1d2ddcbd6118f9dc2b76d2732f08857060a669764dd3847899ed901

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page