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

vllm_openai_chat_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?"
messages = [{"role": "user", "content": prompt}]

chat_completion = openai.ChatCompletion.create(
    model=model,
    messages=messages,
    echo=False,
    max_tokens=1500,
    temperature=0.0,
    frequency_penalty=1.1)

question = messages[0]
answer = chat_completion["choices"][0]["message"]
print(f"{question['role']}: {question['content']}")
print(f"{answer['role']}: {answer['content']}")