Metadata-Version: 2.1
Name: ai-shell-loop
Version: 0.1.0
Summary: A command line tool that lets an AI do work for you.
Author: Carlos Freund
Author-email: carlosfreund@gmail.com
License: Apache License 2.0
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: MacOS :: MacOS X
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: openai ==1.45.0
Requires-Dist: pydantic ==2.9.1
Requires-Dist: PyYAML ==6.0.2

# ai-shell-loop
Use openAi's gpt to generate and execute bash commands quickly.

## Installation

```bash
pip install ai-shell-loop
```

### Open AI Key

Set your api key with `export OPENAI_API_KEY='your-api-key'`

See the [official-docs](https://help.openai.com/en/articles/5112595-best-practices-for-api-key-safety)
for more information.


## Development Setup

### Create environment
```bash
sudo apt install python3 python3-pip python3-venv pipx
python3 -m venv venv
source venv/bin/activate  # Activate the virtual environment
pip install -r requirements.txt  # Install dependencies
pip install -r build-requirements.txt  # Install dependencies for doing a build.
```


## Run 

With the virtual python environment activated, inside the project root, run `python -m ai_shell "echo the current time"`


## Build

Run `python -m build`

### Install locally

```
pipx install dist/ai_do-0.1.0-py3-none-any.whl
pipx ensurepath
```
After this, the `ai-do` command should be available anywhere. 

### Deploy to PyPi

```
twine upload dist/ai_do-0.1.0-py3-none-any.whl -u __token__ -p your_pypi_token
```
