Calls a model to perform machine learning and natural language processing (NLP) tasks, such as sentiment analysis, question answering, translation, summarization, and text generation.
Syntax
jsonb AI_CallModel(text model_id, anyelement content);Parameters
Parameter | Description |
model_id | The unique name of an existing model that you want to call. |
content | The input data for the model. Various data types are supported, including texts, images, complex data structures, and records. For more information, see the "Description" section of this topic. |
Return values
Returns a JSON binary (JSONB) object. The JSONB object can be parsed to generate custom results, such as text and image vectors.
Description
Before you call the function, create a model by using the AI_CreateModel function.
The content parameter supports various data types and matches the content parameter specified in the model_in_transform_fn function. You must specify the content parameter when you call the function. For example, if you want to input text into the model, specify the parameter as
content::text.
Examples
Call an existing model to convert text into vectors.
SELECT polar_ai.AI_CallModel('my_text_embedding_model', '风急天高猿啸哀'::text);Sample result:
---
[1.4284451007843018, -2.7454426288604736, 1.5957790613174438, -2.182790756225586, 3.9757323265075684, -3.0645480155944824, 3.613696336746216, -3.484774351119995, -2.174361228942871, 1.0907986164093018, 1.4526909589767456, 1.3686197996139526, 1.4130642414093018, -1.694422721862793, 2.053454637527466, 4.982985973358154, 1.7921278476715088, 2.6027371883392334, 0.1595267355442047, 1.7544844150543213, 2.0501770973205566]