0ut0flin3 / talk2gpt Goto Github PK

please help , i do what your requirements in windows , i do command python app.py , i got this error when try ask something in microphone .

Human: what is Raspberry Pi

Traceback (most recent call last):
File "C:\Users\Lenovo\Desktop\GPTalk-main\GPTalk-main\app.py", line 237, in
main()
File "C:\Users\Lenovo\Desktop\GPTalk-main\GPTalk-main\app.py", line 184, in main
response = openai.Completion.create(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\openai\api_resources\completion.py", line 25, in create
return super().create(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 107, in create
requestor = api_requestor.APIRequestor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\openai\api_requestor.py", line 85, in init
self.api_key = key or util.default_api_key()
^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\openai\util.py", line 186, in default_api_key
raise openai.error.AuthenticationError(
openai.error.AuthenticationError: No API key provided. You can set your API key in code using 'openai.api_key = ', or you can set the environment variable OPENAI_API_KEY=). If your API key is stored in a file, you can point the openai module at it with 'openai.api_key_path = '. You can generate API keys in the OpenAI web interface. See https://onboard.openai.com for details, or email [email protected] if you have any questions.

I have an env file inside the folder with the session API token copied straight from the website dashboard (it has about 50 characters). I run in my terminal: python3 app.py 2>/dev/null

The app starts and says

OPENAI's text-davinci-003

AI Memories loaded

-- and then... nothing happens. Something is missing in the way I set it up.

Does it work on MacOS?

i do pip install gptalk==0.0.4.5 now were put api key and how to run ?

There is a logic flow problem with the memories file: It loads fine, and dumps fine at the end, but each successive request only sends the original request, stored in the variable pr, plus the latest human request.

You can test this out by asking the AI something, then asking it what its previous answer was. It has no clue.

If you update pr as you go, this is solved and the AI will be fully conversational. I assigned the response to a variable a, then update pr it with:

pr = pr+"Human: "+q+"\nAI: "+a+"\n"

WORKING ON IT