CommanDeft is a CLI tool that converts natural language prompts into executable commands or scripts using OpenAI's chat models.
Project description
CommanDeft
CommanDeft is a simple Python CLI tool designed to generate useful shell commands based on user prompts. It utilizes OpenAI's chat models to provide intelligent suggestions and help users compose shell commands quickly and efficiently.
Requirements
- In order to use CommanDeft you will need an OpenAI API Key which will be asked of you during the initial configuration. You can easily get one from HERE
-If you are using Linux you might have to install xclip
using your package manager.
For example, in Debian:
sudo apt-get install xclip
Installation
To install CommanDeft, you can use the following command:
pip install commandeft
Example Usage
-
Generate a shell command based on a prompt:
commandeft --prompt "list all files in the current directory" OR commandeft -p "list all files in the current directory"
This will provide a shell command suggestion based on the given prompt:
> ls -a
-
Run CommanDeft in interactive mode:
commandeft --interactive
This will start CommanDeft in interactive mode, allowing you to input prompts and receive command suggestions directly within the CLI.
-
Re-configure:
commandeft --configure
This will run the configuration flow for CommanDeft, allowing you to set up your preferences and customize the behavior of the tool.
Configuration
During the initial configuration or when running:
commandeft --configure (or -c)
- You can choose the generated answer's
temperature
. Because this tool is geared towards code generation, lower temperatures perform better. More information about temeratures HERE - You can choose the
max_token
value.
⚠️ Keep in Mind that the guided prompt(assistant role prompt + user role prompt without user's prompt) consumes ~70 tokens. The value you specify won't include these tokens. - You will also be asked about the action that will be performed every time when you accept a generated command when running in interactive mode.
The available actions are:
- Running the generated command
- Copying it to the clipboard
Don't worry though, after this you will be asked to apply your selected action on every generation.
Options
Once installed, you can run CommanDeft using the commandeft
command. Here are the available options:
-h, --help
: Show the help message and exit.-v, --version
: Show the version information and exit.-c, --configure
: Configure CommanDeft (Like the one on the first run).-i, --interactive
: Run CommanDeft in interactive mode.-p, --prompt "TEXT"
: Specify your prompt inline.
Contributing
Contributions to CommanDeft are welcome! If you encounter any issues, have suggestions for improvements, or would like to contribute code, please check out the project repository on GitHub: Repo
License
This project is licensed under the MIT License. See the LICENSE file for more details.
Feedback
If you find CommanDeft useful or have any feedback, I would love to hear from you! Please feel free to reach out and let me know how I can make this tool even better.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file commandeft-0.6.1.tar.gz
.
File metadata
- Download URL: commandeft-0.6.1.tar.gz
- Upload date:
- Size: 20.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: pdm/2.10.1 CPython/3.11.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b3cc69445fdf4dc4847991b7faf3ed78ecd8493ab03a0a4f1af52e4e6f26ce37 |
|
MD5 | f15951e5e76f7a601ade2b1f941538a2 |
|
BLAKE2b-256 | d64540e15571b942e4fd82b0946a9a2b792f12937ed5bfd99cc10bd7842a5bf1 |
File details
Details for the file commandeft-0.6.1-py3-none-any.whl
.
File metadata
- Download URL: commandeft-0.6.1-py3-none-any.whl
- Upload date:
- Size: 18.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: pdm/2.10.1 CPython/3.11.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 23f80e5ce9212c644d7da3d7691e1fa37fb9a8956e1ee1950df3124e84e903cb |
|
MD5 | 84b13e97a0236334ca1df398db19d389 |
|
BLAKE2b-256 | 27a8a0d1dc27a01bac0bb1f03d236c5a7abde7a6c212934d4aca79e2557a995a |