ChatGPT not working

[TwitterBotter]

I tried the new ChatGPT feature but it doesn't work properly, also cannot find the prompt path in tools > settings > ChatGPT > prompt.

Here below are the logs;

ChatGPT token found
No model specified, setting default: gpt-3.5-turbo-03012
Use default model: gpt-3.5-turbo-0301
Use default API: sk-tOoEcfXAc3XBgqbOhAL5T3BlbkFJBpxxxxxxx
chatgpt http: 429
https://api.openai.com/v1/chat/completions
ERROR: chatgpt: Object reference not set to an instance of an object.
(eaexcf) Failed in row: 1
* ERROR absproc: Object reference not set to an instance of an object.
Pausing for: 2
Paused for: 2 seconds
All items: 1
Remaining items: 0

[TwitterBotter]

After update prompt got added into ChatGPT, but still getting the similar error;

chatgpt http: 404
https://api.openai.com/v1/completions
ERROR: chatgpt: Object reference not set to an instance of an object.
(eaexcf) Failed in row: 1
* ERROR absproc: Object reference not set to an instance of an object.
Pausing for: 3
Started: 12/04/2023 13:02 PM
Finished: 12/04/2023 13:02 PM
ID: 1169c119-7f6d-4ea3-a766-5cec746c95ee
Action ran for: 0hr:0min:9s
Action completed as Run in Additional Thread - removing thread
Paused for: 3 seconds
All items: 1
Remaining items: 0

[martin@rootjazz]

As always, submit logs please.


For future reference, please, read through this post and submit your issue accordingly. Not everything will be relevant to your issue, but have a read as it gives an idea of the information you can provide to help me help you as quickly as possible without delays in having to request additional information

https://rootjazz.com/forum/viewtopic.php?f=23&t=1634



Regards,
Martin

[martin@rootjazz]

tried the new ChatGPT feature but it doesn't work properly, also cannot find the prompt path in tools > settings > ChatGPT > prompt.

what version?

HELP >ABOUT


Are you uptodate?
https://rootjazz.com/twitterdub/updatetesting.html



Regards,
Martin

[TwitterBotter]

Hello, I just submitted the logs, it says ID logs_60466!

And yes after update prompt is showing up!

[martin@rootjazz]

the model is being set wrong

"message": "The model `ext-davinci-003` does not exist",

it should be:

text-davinci-003

apparently the program is setting it wrong, but the code, is setting it correctly, so I don't know why the "t" is being lost.

For now, set your CUSTOM MODEL:

TOOLS > SETTINGS > CHAT GPT > MODEL >
text-davinci-003


then it should work, whilst I figure out why the "t" is being removed

[martin@rootjazz]

ok, perhaps you set a custom model and you set it wrong, I read the logs wrong, it might be twitterdub setting it, but equally it could be you. As the code is setting it correctly, I can only assume you've set it.

Next update will log clearer to know more



Regards,
Martin

[TwitterBotter]

Hello,

I also try to leave it empty so it would use the default settings, and even with the correct "text-davinci-003" it still shows up the same error.
I am sure that the API key is correct, or do I need to purchase a premium subscription for ChatGPT?

I just uploaded another log, the ID is log_31547~

Thanks!

[martin@rootjazz]

Hello,

I also try to leave it empty so it would use the default settings, and even with the correct "text-davinci-003" it still shows up the same error.

oh, let me check the logs, but the "t" is getting lost / removed for some reason. No idea why. Let me just add a check for "ext-davinci-003" and correct it. No idea why it's necessary, but it will fix it and that's the main thing

I am sure that the API key is correct, or do I need to purchase a premium subscription for ChatGPT?

no, free is fine (what I am using

I just uploaded another log, the ID is log_31547~

let me check

[martin@rootjazz]

ok, when you went to the default version it worked:

00:09:32: Use default model: text-davinci-003
00:09:32: Use default API: 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
00:09:32: Use default prompt: make a reply to this comment like a teenage girl with emoji
00:09:32: chatgpt http: 429
https://api.openai.com/v1/completions

But then the openai server returned a 429, which is a "you are making too many requests" response

https://developer.mozilla.org/en-US/doc ... Status/429

429 Too Many Requests

The HTTP 429 Too Many Requests response status code indicates the user has sent too many requests in a given amount of time ("rate limiting").

A Retry-After header might be included to this response indicating how long to wait before making a new request.

So either, openai doesn't like your IP at all and returns this, or you will hitting their server too much (which I cannot think you were...)


Please, can you try again and see what happens. and let me know