LLM_EXTRACT

描述

用于从文本中提取特定标签对应的信息

语法

LLM_EXTRACT([<resource_name>], <text>, <labels>)

参数

参数	说明
<resource_name>	指定的资源名称，可空
<text>	要提取信息的文本
<labels>	要提取的标签数组

返回值

返回一个包含所有提取标签及其对应值的字符串

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

SET default_llm_resource = 'resource_name';
SELECT LLM_EXTRACT('Apache Doris is an MPP-based real-time data warehouse known for its high query speed.', 
                  ['product_name', 'architecture', 'key_feature']) AS Result;

+---------------------------------------------------------------------------------------+
| Result                                                                                |
+---------------------------------------------------------------------------------------+
| product_name="Apache Doris", architecture="MPP-based", key_feature="high query speed" |
+---------------------------------------------------------------------------------------+

SELECT LLM_EXTRACT('resource_name', 'Apache Doris began in 2008 as an internal project named Palo.',
                  ['original name', 'founding time']) AS Result;

+----------------------------------------+
| Result                                 |
+----------------------------------------+
| original name=Palo, founding time=2008 |
+----------------------------------------+