The plugin allows you to configure the following settings:
OpenAI API Key: Enter your OpenAI API key here to use the plugin.
Model: The default model is 'text-davinci-003' (best)
Temperature: Set the temperature parameter to control the creativity of the generated replies. The default temperature is 0.9.
Max Tokens: Set the maximum number of tokens to generate for the reply. The default value is 100.
Top P: Set the top-p parameter to control the diversity of the generated replies. The default value is 1.
Frequency Penalty: Set the frequency penalty parameter to control the likelihood of the same word being repeated in the generated replies. The default value is 0.0.
Presence Penalty: Set the presence penalty parameter to control the likelihood of the same word being present in the generated replies. The default value is 0.0.