NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}？

Zhou, Jie （周杰） 20

running test code:

deployment_name = 'gpt-4o-v1' #This will correspond

client = AzureOpenAI(

azure_endpoint = "https://****.openai.azure.com/" ,

api_key='**',

api_version = '2024-05-13'

)

print('### using gpt-4o-v1 ...')

chat_messages = [{"role": "system", "content": "You are an experienced assistant of Elekta . You know the products of Monaco very well. You can answer any questions about Elekta and Monaco."}]

rsp = openai.ChatCompletion.create(

rsp = client.chat.completions.create(

model = deployment_name,

messages = chat_messages,

temperature = 0

)

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

then occur error:

Traceback (most recent call last):

File "C:\Users\Administrator\AppData\Local\Temp\1\ipykernel_16000\2497901775.py", line 10, in <module>

rsp = client.chat.completions.create(

File "C:\ProgramData\Anaconda3\envs\dbgpt_env\lib\site-packages\openai_utils_utils.py", line 274, in wrapper

return func(*args, **kwargs)

File "C:\ProgramData\Anaconda3\envs\dbgpt_env\lib\site-packages\openai\resources\chat\completions.py", line 668, in create

return self._post(

File "C:\ProgramData\Anaconda3\envs\dbgpt_env\lib\site-packages\openai_base_client.py", line 1260, in post

return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))

File "C:\ProgramData\Anaconda3\envs\dbgpt_env\lib\site-packages\openai_base_client.py", line 937, in request

return self._request(

File "C:\ProgramData\Anaconda3\envs\dbgpt_env\lib\site-packages\openai_base_client.py", line 1041, in _request

raise self._make_status_error_from_response(err.response) from None

NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}

do you know how to fix this?

this model is worked in Chat playground, but not work by API.

navba-MSFT 23,625 Reputation points Microsoft Employee

2024-09-04T08:59:18.7766667+00:00
@Zhou, Jie （周杰） Welcome to Microsoft Q&A Forum, Thank you for posting your query here!

.

Please change the api-version in your code to use any of the below versions depending on your model and then test again.

.

If you are performing a programmatic deployment, the model name and their versions are:

gpt-4o Version 2024-08-06

gpt-4o, Version 2024-05-13 or 2024-02-15-preview

gpt-4o-mini Version 2024-07-18

Awaiting your reply.
Zhou, Jie （周杰） 20 Reputation points

2024-09-05T05:57:07.9066667+00:00
Hi NM,

thank you for your reply. i deploy new vision of gpt-4o on Azure AI Studio and testing:

client = openai.AzureOpenAI(

azure_endpoint="https://**.openai.azure.com/", api_key='****', api_version='2024-08-06'

)

response = client.chat.completions.create(

model='gpt-4o-com',## my deployname messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Knock knock."}, {"role": "assistant", "content": "Who's there?"}, {"role": "user", "content": "Orange."}, ], temperature=0,

)

print(f"{response.choices[0].message.role}: {response.choices[0].message.content}")

it also error:

Traceback (most recent call last):

Cell In[12], line 6

response = client.chat.completions.create(

File ~\AppData\Local\anaconda3\envs\mamba2\lib\site-packages\openai_utils_utils.py:274 in wrapper

return func(*args, **kwargs)

File ~\AppData\Local\anaconda3\envs\mamba2\lib\site-packages\openai\resources\chat\completions.py:668 in create

return self._post(

File ~\AppData\Local\anaconda3\envs\mamba2\lib\site-packages\openai_base_client.py:1260 in post

return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))

File ~\AppData\Local\anaconda3\envs\mamba2\lib\site-packages\openai_base_client.py:937 in request

return self._request(

File ~\AppData\Local\anaconda3\envs\mamba2\lib\site-packages\openai_base_client.py:1041 in _request

raise self._make_status_error_from_response(err.response) from None

NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
navba-MSFT 23,625 Reputation points Microsoft Employee

2024-09-05T07:43:55.7333333+00:00

@Zhou, Jie （周杰） Thanks for getting back and clarifying. Please use either of the api-versions and that should help api_version="2024-07-01-preview" OR api_version="2024-05-01-preview". More info here.

Hope this helps.
navba-MSFT 23,625 Reputation points Microsoft Employee

2024-09-06T05:30:38.8366667+00:00

@Zhou, Jie （周杰） A quick follow-up to check if you tried my above suggestion to use the api_version="2024-07-01-preview" OR api_version="2024-05-01-preview". More info here.

Awaiting your reply.
Zhou, Jie （周杰） 20 Reputation points

2024-09-06T06:51:49.93+00:00

if use the api_version="2024-07-01-preview" OR api_version="2024-05-01-preview"

the new error is:

AuthenticationError: Error code: 401 - {'error': {'code': 'Unauthorized', 'message': 'Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.'}}

if deploy new model version, there is no other options:
navba-MSFT 23,625 Reputation points Microsoft Employee

2024-09-06T06:57:18.2633333+00:00
@Zhou, Jie （周杰） Thanks for your reply.

Questions:

May I know the region where you have deployed your Azure OpenAI resource ?

Which model is it Gpt4o or gpt40-mini ?

Awaiting your reply.
Deleted

This comment has been deleted due to a violation of our Code of Conduct. The comment was manually reported or identified through automated detection before action was taken. Please refer to our Code of Conduct for more information.
Deleted

This comment has been deleted due to a violation of our Code of Conduct. The comment was manually reported or identified through automated detection before action was taken. Please refer to our Code of Conduct for more information.
navba-MSFT 23,625 Reputation points Microsoft Employee

2024-09-11T04:52:46.8233333+00:00

@Zhou, Jie （周杰） Just following up to check if my suggestion helped. Please let me know if you have any further queries. I would be happy to help.
navba-MSFT 23,625 Reputation points Microsoft Employee

2024-09-12T04:17:49.19+00:00

@Zhou, Jie （周杰） A quick follow-up to check if you had a chance to look at my above comment. Awaiting your reply.

2 answers

Deleted

This answer has been deleted due to a violation of our Code of Conduct. The answer was manually reported or identified through automated detection before action was taken. Please refer to our Code of Conduct for more information.

Comments have been turned off. Learn more
navba-MSFT 23,625 Reputation points Microsoft Employee

2024-09-09T05:28:38.2266667+00:00

@Zhou, Jie （周杰） Thanks for your reply. You can select any versions listed in the model dropdown as shown below:

But while calling the Azure Open AI endpoint from your python application, you can use api_version="2024-07-01-preview" OR api_version="2024-05-01-preview" or api_version="2024-04-01-preview".

Also note, while testing it from the Chat Playground, I confirmed that the Azure Open AI studio chat playground is using 2024-04-01-preview version see below:

If you are encountering the below error:

AuthenticationError: Error code: 401 - {'error': {'code': 'Unauthorized', 'message': 'Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.'}}

Please ensure that you are using the correct API key from the Keys and Endpoints section in your Azure Open AI:

Hope this helps.
Please sign in to rate this answer.

0 comments No comments
Sign in to comment

Use comments to ask for clarification, additional information, or improvements to the question.

Your answer