How should I configure it so that it always uses the actual data instead of sample data?

[HappyGO2023]

sdf = SmartDataframe(df, config={ "llm": llm, "enable_cache": False, "use_error_correction_framework": True, "verbose": True, "enforce_privacy": False }) Currently, with this configuration, sometimes the generated code uses the dataframe source like # Assuming dfs is already declared and contains the dataframes df = dfs[0], while other times it uses sample data with the comment # Sample data provided in the dataframe format. This seems to be random. How should I configure it so that it always uses the actual data instead of sample data?