Intro to Settings

To access WP Wand’s settings, go to WP Wand > Settings from WordPress menu.

Here’s the screenshot of a default settings panel of WP Wand.

We will briefly explain all the options for better understanding and usages.

OpenAI API Key

WP Wand operates with OpenAI API. So, you need to connect your API key here. We have already covered this in the previous article.

Model

OpenAI provides different types of AI models. You’ll find all public content based API model in this list.

1. GPT-3.5-Turbo or ChatGPT: ChatGPT models are optimized for dialogue. But in WP Wand, you can use it for regular usages without the dialogue style. The performance of gpt-3.5-turbo is on par with Instruct Davinci.
2. Davinci: Davinci is the most powerful instruct based model in OpenAI.
3. There are 3 other models you can try using: Curie, Babbage, Ada

For pricing idea, visit OpenAI’s Pricing Page Here

Default Content Language

Select your default AI generated content language from here. You can always change the output content language on our AI generation sidebar while generating.

Temperature

Temperature is a parameter that influences the creativity or randomness of the generated text. It controls the level of uncertainty or randomness in the AI model’s responses.

When the temperature is set to a higher value, such as 1.0, the generated text becomes more diverse and creative. The AI model is more likely to produce unexpected or surprising responses, incorporating a wider range of possibilities.

On the other hand, when the temperature is set to a lower value, like 0.2, the generated text becomes more focused and deterministic. The AI model tends to produce more repetitive or conservative responses, relying on its most likely predictions.

We recommend to keep the Temperature value 1.

Max Token

Max Token lets you set a maximum limit on the length of the generated text, helping you manage and control the size of the output.

If you generate longer blog post most of the time, set the Max Token to the maximum level (here 370). This will allow you to generate longer articles (~1500 words) without any break.

If you want to save your money more, you can keep the max token to our default settings.

Presence Penalty

Presence Penalty is a feature in the OpenAI API that allows you to control the amount of repetition in the generated text. It helps in reducing the tendency of the AI model to repeat certain phrases or words too frequently in its responses. By adjusting the Presence Penalty value, you can influence how often the AI model repeats information.

Frequency

Frequency refers to how often a particular word or phrase appears in a given text. In the context of the OpenAI API, frequency is used to specify the desired occurrence of a specific word or phrase in the generated output. By setting a higher frequency value for a word or phrase, users can prompt the AI model to generate more instances of that word or phrase in its response.