45

hey, are you interested in helping out, got that problem.

46

Hero! Thanks for this. Can confirm this was the issue.

47

Thank you so much!!! I was searching for a solution from so my time

48

Hi, I’m currently using openai-1.1.1 version. But I’m still getting this error. module ‘openai’ has no attribute ‘ChatCompletion’

49

Welcome to the OpenAI community, @spoorthyan20!

Here’s how you can do chat completions with OpenAI Python v1.1.1:

from openai import OpenAI

client = OpenAI(
    # api_key defaults to os.environ.get("OPENAI_API_KEY")
    api_key="My API Key",
)

chat_completion = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "Say this is a test",
        }
    ],
    model="gpt-3.5-turbo",
)

source

2 Likes
50

thanks, do you have the API Reference or some examples in the documentation?
This: OpenAI Platform is a little sparse and I’d love to understand the new api better.

1 Like
51

Hi @ollibolli

Welcome to the community.

Here are some resources for you:

52

Unfoftunetly dont work in Googke Colab notebook. Any othrr ideas?

53

However, if one tries to get the chatbot response using:
response['choices'][0]['message']['content'] as describes here OpenAI Platform

One gets: TypeError: ‘ChatCompletion’ object is not subscriptable

I would like to mention, that this should be fixed din the documentation to:

content = response.choices[0].message.content

3 Likes
54

It works in in Google Colab. Try:

from openai import OpenAI

client = OpenAI(
api_key=“Your API KEY”,
)

chat_completion = client.chat.completions.create(
messages=[
{
“role”: “user”,
“system”: “xxxxx”,
“content”:“xxxxxx”
}
],
model=“gpt-XXXX”,
max_tokens= XXXX,
)

print(chat_completion.choices[0].message.content)

1 Like
55

Thanks it work for me pip install openai==0.27.8

1 Like
56

image
image1920×1080 345 KB

Guys could someone help me with this?

57

I’m getting this now! AttributeError: module ‘openai’ has no attribute ‘Completion’

58

I fixed this issue by uninstalling OpenAI:

pip3 uninstall openai

Then reinstalling it:

pip3 install openai
59

Getting this error just today, worked yesterday without issues.

1 Like
60

Came to this issue on Google Colab. The following works:

!pip3 install openai

from openai import OpenAI
from google.colab import userdata

client = OpenAI(
    api_key=userdata.get('OPENAI_API_KEY'),
)
def llm_response(prompt):
    response = client.chat.completions.create(
        model='gpt-3.5-turbo',
        messages=[{'role':'user','content':prompt}],
        temperature=0
    )
    return response.choices[0].message.content

prompt = '''
    Classify the following review 
    as having either a positive or
    negative sentiment:

    The banana pudding was really tasty!
'''

response = llm_response(prompt)
print(response)

image
image598×523 16.3 KB

61

Perhaps when posting in this thread someone could spend thirty seconds of reading, install “openai classic”, and press the thanks button for the answer above…

pip install "openai<1.0.0"

Or alternately code for the new methods of the API library changes.

If OpenAI had given anyone a heads up instead of jumping from 1.0.0beta2 all the way to 1.1.1 internal and dumping wheels on those millions of developers, maybe a generous person could have written and put in a pull request for another cookbook notebook to be put up “how this all works without paying for a 3rd party code-conversion service, all the way from simple calls up to asyncio streaming multimodal multi-client with token-counting chat history client management”

5 Likes
62

I had the same problem, while using skll library

The only solution was to install openai version 0.28.1

pip install openai==0.28.1

1 Like
63

thanks…this works for me…i m using ubuntu on wsl2 and vscode

64

The error you’re encountering indicates that ChatCompletion is not a subscriptable object, meaning you can’t use indexing ([]) directly on it. It seems like the response object is not a dictionary, but an instance of a ChatCompletion class.

When dealing with a class instance, you would typically access its attributes using dot notation. If you are using the OpenAI Python client, the attributes of the ChatCompletion object would be accessed accordingly. However, the output structure seems to suggest that it should be possible to subscript it if it were a dictionary.

Here is how I fixed this:

# Assuming 'response' is an instance of a ChatCompletion or similar class 

message_content = response.choices[0].message.content 

print(message_content)

Using the period instead of the bracket worked.

1 Like