Skip to main content

Command Line AI- this tool lets you call ChatGPT from a CLI

Project description

ezclai

Command Line AI- this tool lets you call ChatGPT from a CLI.

I'm designing this to be used in conjunction with a fork of shin, which will allow you to call ezclai from any textbox in your computer. Finally, ChatGPT everywhere!

The long-term vision for this project is to add support for extracting context. For example, it would read the current text on a window and be able to add to it, or answer questions about it.


PyPI version Test Status Lint Status codecov Code style: black Imports: isort


Read Latest Documentation - Browse GitHub Code Repository


Installation

  1. The recommended installation method is to use pipx, via

    pipx install ezclai
    

    Optionally, install tesseract so that ezclai can read the screen context and send that along with requests:

    sudo apt install tesseract-ocr scrot python3-tk python3-dev
    
  2. Then go to OpenAI and create an API Key. Once it's generated, add the following to your ~/.profile:

    export OPENAI_API_TOKEN=<paste here>
    
  3. The best way to use this tool is in conjunction with the tool shin, which allows you to run arbitrary bash commands in any textbox in a linux computer, using ibus. To use that, install 'shin' via the fork above, then configure it in your ~/.profile to call ezclai by default:

    export SHIN_DEFAULT_COMMAND="ezclai"
    
  4. Log out then log back in for the changes to take effect!

Usage

Invoke the assistant with the format ezclai <your prompt>. For example:

ezclai Write an email saying I'll be late to work because I'm working on commandline AIs

Development

Installing python dependencies

poetry install

Running Tests

pytest .

Formatting Code

bash .github/format.sh

Linting

bash .github/check_lint.sh

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

ezclai-0.3.1.tar.gz (5.9 kB view details)

Uploaded Source

Built Distribution

ezclai-0.3.1-py3-none-any.whl (7.8 kB view details)

Uploaded Python 3

File details

Details for the file ezclai-0.3.1.tar.gz.

File metadata

  • Download URL: ezclai-0.3.1.tar.gz
  • Upload date:
  • Size: 5.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.6.1 CPython/3.11.4 Linux/6.5.6-76060506-generic

File hashes

Hashes for ezclai-0.3.1.tar.gz
Algorithm Hash digest
SHA256 4d7c604cfb06f89f05a397b0c94f680b7dc0b8c78d697559575ba8d8d31af8c4
MD5 c3dbb4f23ae0fd01fbf3c037f8bfaa8a
BLAKE2b-256 e4cdaaf5b257403fdcd3864d0bb1e85a200529c37d79a275a4ab90ccb23cca0a

See more details on using hashes here.

File details

Details for the file ezclai-0.3.1-py3-none-any.whl.

File metadata

  • Download URL: ezclai-0.3.1-py3-none-any.whl
  • Upload date:
  • Size: 7.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.6.1 CPython/3.11.4 Linux/6.5.6-76060506-generic

File hashes

Hashes for ezclai-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 9e49f42ddb17e0bf7a16d2f38bfdc7d716c984b46771c3f8ede3bf392e662a42
MD5 ec758709d1b2415d216e7730aeec0749
BLAKE2b-256 8ee03ea39a94f5f99ef471575c60a8c2d2c341dc980ae7680ed81d38eb3b876a

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