Artificial intelligence functions
Artificial intelligence (AI) functions allow you to work with large language models (LLMs) and Core ML models. For LLMs, these functions get and convert embedding vectors, compute cosine similarity and token counts, and provide information about table schema. For Core ML models, the remaining functions return information about and perform the evaluation of a model.
| Function | Purpose |
|---|---|
|
Adds two embedding vectors and returns the result as a normalized vector. |
|
|
Returns a JSON object containing the result of the Core ML model evaluation. |
|
|
Returns the similarity between two embedding vectors as a number between -1 (opposite) and 1 (similar). |
|
|
Sends input data to an embedding model and returns a vector representation as container data. |
|
|
Converts an embedding vector from text format to binary container data. |
|
|
Converts an embedding vector from binary container data to text format. |
|
|
Returns a list of the fields on a layout as JSON data. |
|
|
Returns metadata in JSON format about a named model that's currently loaded. |
|
|
Returns information about the specified RAG space or all RAG spaces, if no space ID is specified. |
|
|
Returns table information in Data Definition Language (DDL) format for a list of table occurrences specified as a JSON array. |
|
|
Returns the token count for the specified text. Use for guidance only; actual counts used by models may vary. |
|
|
Normalizes an embedding vector. If specified, the dimension parameter reduces the number of vector dimensions to use before normalizing. |
|
|
Returns the predicted value from a trained regression model for the specified text embedding vector. |
|
|
Subtracts embedding vector v2 from v1 and returns the result as a normalized vector. |