云数据库 SelectDB 版：AI_SIMILARITY

语法

AI_AI_SIMILARITY([<resource_name>], <text_1>, <text_2>)

参数

返回值

• 返回一个 0 - 10 之间的浮点数。0 表示无相似性，10 表示强相似性；数值越高，则说明相似性越高。

• 当输入有值为 NULL 时返回 NULL。

• 结果为大模型生成，所以返回内容并不固定。

示例

假设我有如下表，代表某家快递公司收到的评论：

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

当我想按顾客语气情绪对评论进行排行时可以：

SELECT comment,
    AI_SIMILARITY('resource_name', 'I am extremely dissatisfied with their service.', comment) AS score
FROM user_comments ORDER BY score DESC LIMIT 5;

查询结果大致如下：

+-------------------------------------------------+-------+
| comment                                         | score |
+-------------------------------------------------+-------+
| It arrived broken and I am really disappointed. |   7.5 |
| Delivery was very slow and frustrating.         |   6.5 |
| Not bad, but the packaging could be better.     |   3.5 |
| It is fine, nothing special to mention.         |     3 |
| Absolutely fantastic, highly recommend it.      |     1 |
+-------------------------------------------------+-------+