Cloudera AI Inference service using OpenAI Python SDK client on a local machine

Consider the following guidelines for Cloudera AI Inference service using OpenAI Python SDK client.

Specify the CDP_TOKEN as the API_KEY. A common way is to export CDP_TOKEN as an environment variable and access that from your Python code:

from openai import OpenAI
import os

API_KEY = os.environ['CDP_TOKEN']
MODEL_ID = [***MODEL_ID***]

client = OpenAI(
  base_url = "[***BASE_URL***]",
  api_key = API_KEY,
  )

completion = client.chat.completions.create(
  model=MODEL_ID,
  messages=[{"role":"user","content":"Write a one-sentence definition of GenAI."}],
  temperature=0.2,
  top_p=0.7,
  max_tokens=1024,
  stream=True
)

for chunk in completion:
  if chunk.choices[0].delta.content is not None:
    print(chunk.choices[0].delta.content, end="")