Rule: OpenAI List Integer (AI Interpolator OpenAI)

Base data:

Summary:
The OpenAI List Integer field is taking a prompt with possible context and answering a question about it with a integer result and puts it in a integer list field.

When using an OpenAI vision model, you can also use the combination of prompt and image to get the response you want.

Module needed:
AI Interpolator OpenAI

Field types to populate:
List (integer)  (core Options module).

Base Fields types to use as context:

• Text (plain)
• Text (plain, long)
• Text (formatted)
• Text (formatted, long)
• Text (formatted, long, with summary)

Extra Requirements:
You need a paid OpenAI account with API access.

Prompting tips:

If you want it to select/check multiple values, make sure to prompt this.

There is a placeholder for comma and new line separated integer values and human readable values. Which one you choose is depending on which one will be the easiest to pick for the AI. The module automatically translated human readable values to the integer data keys.

Note that if two or more values exists with the same human readable name, it will choose the first one. Use the key list in this case.

Extra Settings:

None

Extra Advanced Settings:

OpenAI Model

The model to use from OpenAI. Read more here about capabilities and more here about pricing.

OpenAI Vision Image

This only shows up if you choose a model that is capable of vision. When that is chosen you can choose an image field here to use as context for your query.

OpenAI Role

If there should be pre-context or understanding on who the GPT should be, please fill out the role here. Should be short if used.

OpenAI Moderation

This runs each query through OpenAI's moderation api. It makes sure that you do not send a query to OpenAI that breaks their content policy, which could leave to account cancellation. There is almost never any reason not to uncheck this, it is free. The only reason would be if you know what you are going to send does not break the content policy and you want to speed up multiple queries.

Possible example use cases:

• Sentiment analysis on a fixed integer curve.
• Rating on a fixed integer curve.
• Categorize stuff that does not need a taxonomy and that should be stored with integer keys.