"""This simple script shows how to interact with an OpenAI-compatible server from a client.""" # import argparse # import modal from openai import OpenAI import os client = OpenAI(api_key=os.getenv("modal_api")) client.base_url = ( "https://alexprincecursor--example-vllm-openai-compatible-serve.modal.run/v1/" ) response = client.chat.completions.create( model="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w4a16", # GPT-4.1 mini messages=[ {"role": "system", "content": "You are a rockstar lyric generator. You are given a song and you need to generate a lyric for it."}, {"role": "user", "content":"The song is 'Bohemian Rhapsody' by Queen."} ], max_tokens=512, temperature=0.7 ) print(response.choices[0].message.content)