WP AI Co-Pilot Settings


WP AI Co-Pilot Settings

API Key:


Language Selection for Text Generation:

Select the desired language for generated text to maintain consistency with your blog post.

  • Choose the language in which you want the generated text to be written.
  • It is essential to maintain consistency between the selected language and the language used in your blog post to ensure accurate and relevant autocomplete results.


Preferred OpenAI Model:

Discover the ideal OpenAI model for your needs.

  • Different models within the OpenAI framework offer varying capabilities.
  • The “davinci” model is the most advanced and powerful, but it comes at a higher cost.
  • On the other hand, the “ada” model is less capable but more affordable.
  • For only text generation, you can select “text-davinci-003”.


Depending on your preferences, you need to choose the right model. For more detailed information about the available models, refer to the OpenAI documentation at https://beta.openai.com/docs/models/gpt-3.


Temperature Control:

Customize the randomness of AI-generated completions by adjusting the temperature parameter. Lower values enhance predictability, while higher values stimulate creativity and randomness.

  • Adjust the temperature parameter to influence the level of randomness in the generated completions.
  • Decreasing the temperature value results in less random outputs, making the model more deterministic and repetitive.
  • Conversely, as the temperature approaches one, the model becomes more creative and generates more random completions.<


Maximum Tokens:

Control the Length of Generated Text by Defining Maximum Token Limit

  • Define the maximum number of tokens to be generated in a single request.
  • Tokens are the units of text processed by the model, and setting a maximum limit helps manage the length of the generated text.


Top Prediction (Top-P):

A versatile parameter that shapes the diversity of your generated text by defining the number of tokens involved in the creative process.

  • The Top-P (Top Prediction) parameter allows you to control the diversity of the generated text.
  • Adjusting this parameter determines the number of different tokens considered during text generation.


Frequency Penalty:

Where you hold the power to shape the presence of word repetition within your generated text.

  • Utilize the frequency penalty to influence the occurrence of word repetition in the generated text.
  • Higher penalty values discourage word repetition, while lower values may result in increased repetition.


Presence Penalty:

Customize text generation by adjusting the presence penalty.

  • Adjust the presence penalty to influence the inclusion of specific words in the generated text.
  • Higher values encourage the model to incorporate the provided words more frequently, while lower values may reduce their occurrence.


Number of Output Choices:

Customize the number of output choices for your generated text. Easily set the default number and tailor your results to suit your needs.

  • Set the default number of output choices for the generated text.


Image Size Options:

Get the perfect image size for your generated content. Choose from three image size options for the generated content: 

  • Thumbnail (256x256px)
  • Medium (512x512px)
  • Large (1024x1024px)

Was this article helpful to you? No Yes

How can we help?