import openai
from openai import OpenAI


client = OpenAI(base_url="http://localhost:5543/v1", api_key="EMPTY")

models = client.models.list()

model = "hf:neuralmagic/TinyLlama-1.1B-Chat-v0.4-pruned50-quant-ds"
print(f"Accessing model API '{model}'")


# Completion API
stream = False
completion = client.completions.create(
    prompt="The sun shined",
    stream=stream,
    n=8,
    max_tokens=10,
    model=model
)

print(completion)