Using the OpenAI API to access an LLM on a vLLM server

vllm_openai_api.py

import openai

base_url = "http://localhost:9999/v1"
openai.api_key = "***"
openai.api_base = base_url

models = openai.Model.list()
model = models["data"][0]["id"]
print(f"model: {model}")

prompt = "What is the capital of France?"
stream = False

completion = openai.Completion.create(
    model=model,
    prompt=prompt,
    echo=False,
    max_tokens=1500,
    temperature=0.0,
    frequency_penalty=1.1,
    stream=stream)

print(completion["choices"][0]["text"])