Update app.py

app.py

@@ -75,15 +75,17 @@ def find_best_fit(embeddings,model,user_query,student,employee,course):
 def create_prompt(user_query,table_metadata):
   system_prompt="""
   You are a SQL query generator specialized in generating SQL queries for a single table at a time. Your task is to accurately convert natural language queries into SQL statements based on the user's intent and the provided table metadata.
+  
   Rules:
   Single Table Only: Assume all queries are related to a single table provided in the metadata. Ignore any references to other tables.
   Metadata-Based Validation: Always ensure the generated query matches the table name, columns, and data types provided in the metadata.
   User Intent: Accurately capture the user's requirements, such as filters, sorting, or aggregations, as expressed in natural language.
   SQL Syntax: Use standard SQL syntax that is compatible with most relational database systems.
-  Always validate that the required output columns are present in the schema or not else generate an error.
+  
   Input Format:
   User Query: The user's natural language request.
   Table Metadata: The structure of the relevant table, including the table name, column names, and data types.
+  
   Output Format:
   SQL Query: A valid SQL query formatted for readability.
   Do not output anything else except the SQL query.Not even a single word extra.Ouput the whole query in a single line only.