import openai openai.error.InvalidRequestError: Invalid URL (POST /v1/chat/completions)

[Eric0101]

Describe the bug

[ERROR][2023-03-04 18:25:20][chat_gpt_bot.py:68] - Invalid URL (POST /v1/chat/completions)
Traceback (most recent call last):
File "/opt/chatgpt-on-wechat/bot/chatgpt/chat_gpt_bot.py", line 44, in reply_text
response = openai.ChatCompletion.create(
File "/usr/local/lib/python3.9/site-packages/openai/api_resources/chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
File "/usr/local/lib/python3.9/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
File "/usr/local/lib/python3.9/site-packages/openai/api_requestor.py", line 226, in request
resp, got_stream = self._interpret_response(result, stream)
File "/usr/local/lib/python3.9/site-packages/openai/api_requestor.py", line 619, in _interpret_response
self._interpret_response_line(
File "/usr/local/lib/python3.9/site-packages/openai/api_requestor.py", line 679, in _interpret_response_line
raise self.handle_error_response(
openai.error.InvalidRequestError: Invalid URL (POST /v1/chat/completions)

To Reproduce

response = openai.ChatCompletion.create(

openai.error.InvalidRequestError: Invalid URL (POST /v1/chat/completions)

Code snippets

response = openai.ChatCompletion.create(

openai.error.InvalidRequestError: Invalid URL (POST /v1/chat/completions)


[root@vps87388579 chatgpt-on-wechat]# pip3 show openai
Name: openai
Version: 0.27.0
Summary: Python client library for the OpenAI API
Home-page: https://github.com/openai/openai-python
Author: OpenAI
Author-email: support@openai.com
License: None
Location: /usr/local/lib/python3.9/site-packages
Requires: requests, aiohttp, tqdm
Required-by:

OS

centos 8.6

Python version

3.9

Library version

0.27

[mymusise]

If you're requesting your finetune model, try:

response = openai.Completion.create(

[Eric0101]

not finetune model ,i'm request gpt-3-turbo model

[IvoryF]

same problem

[bell99431]

same problem.
The example of official playground has this problem too.
The api crashed maybe.

[lucifer1004]

This seems to be account related. Some accounts are affected while others are not.

[adeolaemmanuelmorren]

same issue in my case I have a loop that calls the api multiple times, bit backoff retry exception handling, and It only does it a few times, in the loop, but not on every one and it seems very unpredictable

[jriskin]

I think they moved the endpoint for the new models. They also seemed to have updated the error...

openai.error.InvalidRequestError: This is a chat model and not supported in the v1/completions endpoint. Did you mean to use v1/chat/completions?

So the maybe the API needs to add '/chat' for gpt-3.5-turbo and gpt-3.5-turbo-0301 models?
The documentation looks like only those two are supported for 'chat completion' but doesn't state that they are losing the normal endpoint. So 🤷🏻‍♀️

https://platform.openai.com/docs/api-reference/chat/create

[javff]

I was able to fix it by updating the openai lib.

pip install --upgrade openai.

Then you can try this:

import openai

completion = openai.ChatCompletion.create(
  model="gpt-3.5-turbo",
  messages=[{"role": "user", "content": "Tell the world about the ChatGPT API in the style of a pirate."}]
)

I got the answer in the official documentation:

https://openai.com/blog/introducing-chatgpt-and-whisper-apis

[calebtote]

I've upgraded via pip and still get the same error.

[fengerzh]

I've upgraded via pip and still get the same error.

You should change from openai.Completion.create to openai.ChatCompletion.create.

[athyuttamre]

This error is expected if using openai.Completion.create with a chat model. Please use openai.ChatCompletion.create instead. This includes gpt-3.5-turbo and gpt-4 (for those with access).