LLM_FILTER

Description

Filters text based on given conditions.

Syntax

LLM_FILTER([<resource_name>], <text>)

Parameters

Parameter	Description
<resource_name>	The specified resource name, optional
<text>	The information to be evaluated

Return Value

Returns a boolean value.

If any input is NULL, returns NULL.

The result is generated by the large language model, so the output may not be fixed.

Example

Suppose you have the following table representing comments received by a courier company:

CREATE TABLE user_comments (
    id      INT,
    comment VARCHAR(500)
) DUPLICATE KEY(id)
DISTRIBUTED BY HASH(id) BUCKETS 10
PROPERTIES (
    "replication_num" = "1"
);

If you want to query the positive comments, you can use:

SELECT id, comment FROM user_comments
WHERE LLM_FILTER('resource_name', CONCAT('This is a positive comment: ', comment));

The result may look like:

+------+--------------------------------------------+
| id   | comment                                    |
+------+--------------------------------------------+
|    1 | Absolutely fantastic, highly recommend it. |
|    3 | This product is amazing and I love it.     |
+------+--------------------------------------------+