Version 1.4.3 is causing chat to not generate responses

[kikkoi]

Which indicates empty 'max tokens' and 'temperature' settings, as they were left as default null. It seems to me that OpenAI ChatGPT does not allow this

[longy2k]

Was your model set as 'gpt-3.5-turbo' and did you have max_token set near 4096?

There might be an error such as:

This model's maximum context length is 4097 tokens. However, you requested 4115 tokens (19 in the messages, 4096 in the completion). Please reduce the length of the messages or completion.

I did not display this error which is why you may have received an empty response.

I will display the error in the next version. Thanks for helping me see this issue :)

If this is not the case, please let me know.

btw, max_tokens and temperature can be left as null. If it is null, max_tokens defaults to inf and temperature defaults to 1.