About openai

Short Course Q&A AI Python for Beginners
1

This is the error I’m facing:

{
“name”: “AttributeError”,
“message”: “module ‘openai’ has no attribute ‘error’”,
“stack”: "---------------------------------------------------------------------------
APIRemovedInV1 Traceback (most recent call last)
File c:\Users\shikh\helper_functions.py:20, in print_llm_response(prompt)
19 raise ValueError("Input must be a string enclosed in quotes.")
—> 20 response = openai.ChatCompletion.create(
21 model="gpt-3.5-turbo",
22 messages=[
23 {
24 "role": "system",
25 "content": "You are a helpful but terse AI assistant who gets straight to the point.",
26 },
27 {"role": "user", "content": prompt},
28 ],
29 temperature=0.0,
30 ).choices[0][‘message’][‘content’]
31 print("*" * 100)

File c:\Users\shikh\AppData\Local\Programs\Python\Python312\Lib\site-packages\openai\lib\_old_api.py:39, in APIRemovedInV1Proxy.call(self, *_args, **_kwargs)
38 def call(self, *_args: Any, **_kwargs: Any) → Any:
—> 39 raise APIRemovedInV1(symbol=self._symbol)

APIRemovedInV1:

You tried to access openai.ChatCompletion, but this is no longer supported in openai>=1.0.0 - see the README at GitHub - openai/openai-python: The official Python library for the OpenAI API for the API.

You can run openai migrate to automatically upgrade your codebase to use the 1.0.0 interface.

Alternatively, you can pin your installation to the old version, e.g. pip install openai==0.28

A detailed migration guide is available here: v1.0.0 Migration Guide · openai/openai-python · Discussion #742 · GitHub

During handling of the above exception, another exception occurred:

AttributeError Traceback (most recent call last)
Cell In[1], line 4
1 from helper_functions import print_llm_response, get_llm_response, get_chat_completion
3 # Example usage
----> 4 print_llm_response("capital of france?")

File c:\Users\shikh\helper_functions.py:37, in print_llm_response(prompt)
35 except TypeError as e:
36 print("Error:", str(e))
—> 37 except openai.error.OpenAIError as e:
38 print("API error:", str(e))
39 time.sleep(60)

AttributeError: module ‘openai’ has no attribute ‘error’"
}

2

Hey it seems you can give this solution a try, downgrade to 0.28 to make it work.
pip install openai==0.28

4

i tried this now my current error is

API error: You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.

and my program didn’t run ones

this is the code :

import os
import openai
from dotenv import load_dotenv
import time

Load the OpenAI API key from the .env file

load_dotenv(‘.env’, override=True)
openai_api_key = os.getenv(‘OPENAI_API_KEY’)

Set up the OpenAI client

openai.api_key = openai_api_key

def print_llm_response(prompt):
“”“This function takes a prompt as input and prints the response from OpenAI’s GPT-3.5 model.”“”
try:
if not isinstance(prompt, str):
raise ValueError(“Input must be a string enclosed in quotes.”)
response = openai.ChatCompletion.create(
model=“gpt-3.5-turbo”,
messages=[
{
“role”: “system”,
“content”: “You are a helpful but terse AI assistant who gets straight to the point.”,
},
{“role”: “user”, “content”: prompt},
],
temperature=0.0,
)[‘choices’][0][‘message’][‘content’]
print(“" * 100)
print(response)
print("” * 100)
print(“\n”)
except TypeError as e:
print(“Error:”, str(e))
except openai.OpenAIError as e: # Using the correct error handling
print(“API error:”, str(e))
time.sleep(60) # Wait for 60 seconds before retrying

def get_llm_response(prompt):
“”“This function takes a prompt as input and returns the response from OpenAI’s GPT-3.5 model.”“”
try:
response = openai.ChatCompletion.create(
model=“gpt-3.5-turbo”,
messages=[
{
“role”: “system”,
“content”: “You are a helpful but terse AI assistant who gets straight to the point.”,
},
{“role”: “user”, “content”: prompt},
],
temperature=0.0,
)[‘choices’][0][‘message’][‘content’]
return response
except openai.OpenAIError as e:
print(“API error:”, str(e))
time.sleep(60) # Wait for 60 seconds before retrying
return None

def get_chat_completion(prompt, history):
“”“This function takes a prompt and a history of previous prompts, returns the response from the model.”“”
try:
history_string = “\n\n”.join([“\n”.join(turn) for turn in history])
prompt_with_history = f"{history_string}\n\n{prompt}"
response = openai.ChatCompletion.create(
model=“gpt-3.5-turbo”,
messages=[
{
“role”: “system”,
“content”: “You are a helpful but terse AI assistant who gets straight to the point.”,
},
{“role”: “user”, “content”: prompt_with_history},
],
temperature=0.0,
)[‘choices’][0][‘message’][‘content’]
return response
except openai.OpenAIError as e:
print(“API error:”, str(e))
time.sleep(60) # Wait for 60 seconds before retrying
return None