I was going through a course in OpenAI's API using an in-browser jupyter notebook page but wanted to copy some example code from there into a local IDE. I installed Python and the jupyter extention in VS Code and the OpenAI library. My code is below:
import openai
import os
# from dotenv import load_dotenv, find_dotenv
# _ = load_dotenv(find_dotenv()) # read local .env file
openai.api_key = "my api key is here"
def get_completion(prompt, model="gpt-3.5-turbo"):
messages = [{"role": "user", "content": prompt}]
response = openai.ChatCompletion.create(
model=model,
messages=messages,
temperature=0, # this is the degree of randomness of the model's output
)
return response.choices[0].message["content"]
prompt = f"""
Determine whether each item in the following list of \
topics is a topic in the text below, which
is delimited with triple backticks.
Give your answer as list with 0 or 1 for each topic.\
List of topics: {", ".join(topic_list)}
Text sample: '''{story}'''
"""
response = get_completion(prompt)
print(response)
I installed Python and imported the openai library. When I run I am getting the error:
APIConnectionError: Error communicating with OpenAI: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))
I'm assuming that's because I commented out lines 3 and 4 in the code because I am unsure what they do and do not know how to use the dotenv library. Is it simple to set this up just to make a basic call to the openai API? That's all I'm trying to do with this code right now.
Usually, you load your API KEY from your .env file but, as you are hardcoding it, you don't need anything else.
The error you are getting might be related to the absence of the topic_list and story definitions.