Issue during installation

[howdid1gethere]

During installation, when i do pentestgpt-connection, i end up with this error.

#### Test connection for OpenAI api (GPT-4)
Traceback (most recent call last):
  File "/home/reed/venv/lib/python3.11/site-packages/pentestgpt/utils/APIs/chatgpt_api.py", line 81, in _chat_completion
    response = openai.ChatCompletion.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_resources/chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
                           ^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_requestor.py", line 298, in request
    resp, got_stream = self._interpret_response(result, stream)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_requestor.py", line 700, in _interpret_response
    self._interpret_response_line(
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_requestor.py", line 765, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: The model `gpt-4` does not exist or you do not have access to it. Learn more: https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/reed/venv/bin/pentestgpt-connection", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/pentestgpt/test_connection.py", line 47, in main
    result, conversation_id = chatgpt.send_new_message("Hi how are you?")
                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/pentestgpt/utils/llm_api.py", line 225, in send_new_message
    response = self._chat_completion(history)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/pentestgpt/utils/APIs/chatgpt_api.py", line 119, in _chat_completion
    response = openai.ChatCompletion.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_resources/chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
                           ^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_requestor.py", line 298, in request
    resp, got_stream = self._interpret_response(result, stream)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_requestor.py", line 700, in _interpret_response
    self._interpret_response_line(
  File "/home/reed/venv/lib/python3.11/site-packages/openai/api_requestor.py", line 765, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: The model `gpt-4` does not exist or you do not have access to it. Learn more: https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4.

Everything i've seen shows that this program worked with 3.5 API keys, why is it complaining that i don't have access to four? is there an option to only use CGPT3.5?

[GreyDGL]

May you provide the complete input for running the tool? You can use gpt-3.5 only by specifying that in the flag.

[rubentimbal]

I am having the same exact issue after installation. Whenever I try to test the connection I receive the same error message.

[howdid1gethere]

My issue was resolved. It turns out, even though you are using the GPT3.5API, you still have to enroll a payment method on the site. It does ultimately cost $5 (minimum tipup). After supplying a payment method, the program works as it should.

[rubentimbal]

Thank you for you answer. I setup a pyment method and added some credits, I created a brand new API key but I keep getting an error mesage that I exceeded my quota, but the openAI website shows no usage so far. I guess I am getting closer.

[howdid1gethere]

Are you setting the key as an environment variable using export OPENAI_KEY=XXXXXX?

On Fri, Dec 1, 2023, 12:32 PM rubentimbal @.***> wrote:

Thank you for you answer. I setup a pyment method and added some credits, I created a brand new API key but I keep getting an error mesage that I exceeded my quota, but the openAI website shows no usage so far. I guess I am getting closer.

— Reply to this email directly, view it on GitHub https://github.com/GreyDGL/PentestGPT/issues/178#issuecomment-1836509515, or unsubscribe https://github.com/notifications/unsubscribe-auth/BDYL4VC2EG5UPVGIDFD7RKTYHIICNAVCNFSM6AAAAAA73FDCAGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQMZWGUYDSNJRGU . You are receiving this because you authored the thread.Message ID: @.***>

[rubentimbal]

Yes, my error message is related to my account it seems. I exceeded my quota, which is false. I read in a forum that sometimes it could take up to 48 hours for the new payment method to appear. I will try again tomorrow. Thanks for your help. I will let you know if it works.