Curl works but Python fails for the same API key and same request

[tristandeborde]

Describe the bug

I'm trying to use the ChatCompletion API by following the documentation examples.
I'm getting: openai.error.InvalidRequestError: Invalid URL (POST /v1/engines/gpt-3.5-turbo/chat/completions)

• I did check that I'm using ChatCompletion and not Completion.
• I generated another API key to solve the problem.

This is strictly a bug from the Python lib since using curl, the POST request works.

⚠️ I feel like I should mention I was recently accepted in the GPT-4 beta (according to an email I've received), so it may be due to this ?

Thanks in advance for your help.

To Reproduce

Just use the ChatCompletion python example from the docs. This worked fine for me until 2 weeks ago.

Code snippets

import openai
openai.api_key="myAPIkey"
openai.organization = "myorg" # I've tried without this as well
openai.ChatCompletion.create(engine="gpt-3.5-turbo",messages=[{"role": "user", "content":"yo"}])
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Users/tristan/miniforge3/lib/python3.10/site-packages/openai/api_resources/chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
  File "/Users/tristan/miniforge3/lib/python3.10/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
  File "/Users/tristan/miniforge3/lib/python3.10/site-packages/openai/api_requestor.py", line 226, in request
    resp, got_stream = self._interpret_response(result, stream)
  File "/Users/tristan/miniforge3/lib/python3.10/site-packages/openai/api_requestor.py", line 619, in _interpret_response
    self._interpret_response_line(
  File "/Users/tristan/miniforge3/lib/python3.10/site-packages/openai/api_requestor.py", line 679, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: Invalid URL (POST /v1/engines/gpt-3.5-turbo/chat/completions)

The above code fails, but this works!

curl https://api.openai.com/v1/chat/completions \                          
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
     "model": "gpt-3.5-turbo",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
   }'
{"id":"....","object":"chat.completion","created":1680624274,"model":"gpt-3.5-turbo-0301","usage":{"prompt_tokens":14,"completion_tokens":5,"total_tokens":19},"choices":[{"message":{"role":"assistant","content":"This is a test!"},"finish_reason":"stop","index":0}]}

OS

macOS Monterey 12.6

Python version

Python 3.10.6, but fails also in python:3.10 docker image

Library version

openai-python v0.27.0, also v0.27.3

[tristandeborde]

My bad !
I made the mistake of using the key "engine":

openai.ChatCompletion.create(engine="gpt-3.5-turbo",messages=[{"role": "user", "content":"yo"}])

instead of model:

openai.ChatCompletion.create(model="gpt-3.5-turbo",messages=[{"role": "user", "content":"yo"}])