Chat Completion with Local Server

This project demonstrates how to use the OpenAI API for chat completions with a local server setup. It allows users to input prompts via command-line arguments and receive responses from a specified model.

Prerequisites

• Python 3.x
• mlx-omni-server installed

Installation

1. Install the mlx-omni-server:

   pip install mlx-omni-server

2. Start the local server:

   mlx-omni-server

Usage

Run the script from the command line, providing a prompt as an argument:

uv run main.py "What is the capital of Argentina?"

Feel free to modify any sections to better fit your project's specifics!