Metadata-Version: 2.1
Name: pythoness
Version: 0.0.3
Summary: TBD.
Author-email: Emery Berger <emery.berger@gmail.com>
Project-URL: Homepage, https://github.com/plasma-umass/pythoness
Project-URL: Bug Tracker, https://github.com/plasma-umass/pythoness/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: openai (>=0.27.0)
Requires-Dist: click (>=8.1.3)

# Pythoness

Pythoness is a Python module that uses OpenAI's GPT-4 model to automatically generate Python code based on natural language descriptions of the desired functionality.

## Installation

The easiest way to install Pythoness is through pip:

```bash
python3 -m pip install pythoness
```

## Usage

To use Pythoness, you will need to import the `pythoness` module and use the `@pythoness.spec` decorator to specify the desired functionality. Here is an example usage:

```python
import pythoness

@pythoness.spec("Compute the nth number in the Fibonacci series.")
def myfib(n: int) -> int:
    ""
```

This code will generate a Python function named `myfib` that computes the nth number in the Fibonacci series.

To actually execute the function, you can call it as you would any other Python function:

```python
for i in range(20):
    print(myfib(i))
```

Pythoness caches the results of translating natural language to Python, so subsequent executions in the same directory will run much faster.

