Artificial intelligence script steps

Sets up an AI account to use by name, given a model provider (or endpoint) and an API key.

Loads a Core ML (Machine Learning) model and prepares it for use.

Sets up a prompt template to use by name in other AI script steps, given a model provider and predefined prompts you can customize.

Sets up a RAG account to use by name, given an endpoint and an API key.

Trains, saves, loads, and unloads a regression model. Trains a model based on embedding vectors for text data and numeric target data.

Fine-tunes a model with the specified training data set.

Gets a text response from an AI model given a user prompt.

Sends input data to an embedding model and inserts the returned vector representation into a field or variable.

For every record in the found set, sends data from a source field to an embedding model and inserts the returned vector representation into a target field.

Sends an image to an image captioning model and inserts the returned caption into a field or variable.

For every record in the found set, sends an image from a source field to an image captioning model and inserts the returned caption into a target field.

Sends a natural language prompt and a list of fields on the current layout to a model, which returns a FileMaker find request, and performs a find.

Sends a prompt to, or adds and removes data from, a RAG space on the AI model server specified by a RAG account.

Performs a semantic find in a target field for the specified text, image, or embedding vectors.

Sends a natural language prompt and database schema to a model, which sends back an SQL query to get a result from the database to use in its response.