This old format doesn;t supported anymore

[lucasjinreal]

Confirm this is an issue with the Python library and not an underlying OpenAI API

• This is an issue with the Python library

Describe the bug

response = client.chat.completions.create(
# model="alibaba/Qwen1.5-110B-Chat",
model="Qwen/Qwen2-7B-Instruct",
messages=[
{
"role": "system",
"content": [{"type": "text", "text": "you are a dog"}],
"name": "",
},
{
"role": "user",
"content": [{"type": "text", "text": "你好啊"}],
"name": "",
},
{
"role": "assistant",
"content": [
{
"type": "text",
"text": "你好，我是一条狗，我叫汪昂",
}
],
"name": "",
},
{
"role": "user",
"content": [{"type": "text", "text": "Hello"}],
"name": "",
},
],
stream=True,
)

Am using openai to create, got request format error:

openai.BadRequestError: Error code: 400 - {'code': 50400, 'message': 'The request parameter is invalid, Please check again.', 'data': None, 'error': 'The request parameter is invalid, Please check again.'}

this format previous works OK> why?

To Reproduce

gyiguy

Code snippets

No response

OS

macOS

Python version

3.11

Library version

openai latest

[mophilly]

I also ran into this. python replied with "You tried to access openai.ChatCompletion, but this is no longer supported in openai>=1.0.0" Now that is true in the form of the code below, but I also got the similar error using the client.chat.completions.create form.

Code snippet
response = openai.ChatCompletion.create( model="gpt-4", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": prompt} ], max_tokens=1000, temperature=0.7, )

OS
MacOS Sonoma (14.5)

Python Version
Python 3.12

Library version
openai v1.35.8.