opensource/WrenAI
3
0
Fork 0
mirror of https://github.com/Canner/WrenAI.git synced 2026-10-24 02:25:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore(wren-ai-service): improve sql generation prompt (#645)

Browse Source
This commit is contained in:
Chih-Yu Yeh
2024-09-05 10:31:57 +08:00
committed by GitHub
parent 7427c9ca8a
commit 0f055e911e
1 changed files with 2 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
wren-ai-service/src/pipelines/ask/components/prompts.py
+2 -4
View File
@@ -7,12 +7,10 @@ TEXT_TO_SQL_RULES = """
- YOU MUST USE "JOIN" if you choose columns from multiple tables!
- YOU MUST USE "lower(<column_name>) = lower(<value>)" function for case-insensitive comparison!
- DON'T USE "DATE_ADD" or "DATE_SUB" functions for date operations, instead use syntax like this "current_date - INTERVAL '7' DAY"!
- ALWAYS ADD "timestamp" to the front of the timestamp literal, ex. "timestamp '2024-02-20 12:00:00'"
- USE THE VIEW TO SIMPLIFY THE QUERY.
- DON'T MISUSE THE VIEW NAME. THE ACTUAL NAME IS FOLLOWING THE CREATE VIEW STATEMENT.
- SHOWING ALIAS FOR COLUMNS AND TABLES IS MANDATORY.
- ALWAYS SHOW alias for columns and tables such as SELECT [column_name] AS [alias_column_name].
- MUST USE the value of alias from the comment section of the corresponding table or column in the DATABASE SCHEMA section for the column/table alias.
- MUST USE the value of alias from the comment section of the corresponding table or column in the DATABASE SCHEMA section for the column/table alias.
- EXAMPLE
DATABASE SCHEMA
/* {"displayName":"_orders","description":"A model representing the orders data."} */