PolarDB:NL2SQL_SUMMARY: Result summarization

Step 1: Generate a SQL query statement

Use the NL2SQL model to convert your question into SQL:

/*polar4ai*/SELECT * FROM PREDICT (MODEL _polar4ai_nl2sql, select 'Query the credit score of each merchant') WITH (basic_index_name='schema_index',pattern_index_name='pattern_index');

The model returns a SQL query statement. For example:

SELECT merchname AS merchant_name, limitscore AS credit_score FROM hkrt_merchant_info ORDER BY limitscore;

Tip: Review the generated SQL before passing it to NL2SQL_SUMMARY. Confirming that the query matches your intent helps ensure the summary is accurate.

Copy the generated SQL query statement. You will use it in the next step.

Step 2: Generate a summary

Pass the SQL query statement to NL2SQL_SUMMARY, replacing <SQL_statement> and <usr_query> with your values:

/*polar4ai*/SELECT * FROM PREDICT (MODEL _polar4ai_nl2sql_summary,<SQL_statement> WITH (usr_query = <usr_query>);

Parameters

Example

/*polar4ai*/SELECT * FROM PREDICT (MODEL _polar4ai_nl2sql_summary,
SELECT merchname AS merchant_name, limitscore AS credit_score FROM hkrt_merchant_info ORDER BY limitscore
 ) WITH (usr_query='Query the credit score of each merchant');

Output:

This query returned the credit scores for 15 merchants, ranging from 60 to 95. The lowest score is 60 (Future Star Merchant), and the highest is 95 (Tech City Merchant). Overall, most merchants have scores above 70, indicating good credit standing.

SQL query results: