types.DataSource

DataSource()

An abstract class defining the interface for data sources used by QueryChat.

This class is generic over the DataFrame type returned by execute_query, test_query, and get_data methods.

Attributes

Name	Type	Description
table_name	str	Name of the table to be used in SQL queries.

Name	Description
cleanup	Clean up resources associated with the data source.
execute_query	Execute SQL query and return results.
get_column_metas	Return column names and types without running stats queries.
get_data	Return the unfiltered data.
get_data_description	Get a human-readable data description for the system prompt.
get_db_type	Name for the database behind the SQL execution.
get_schema	Return schema information about the table as a string.
get_semantic_views_description	Get information about semantic views (if any) for the system prompt.
populate_column_stats	Populate min/max/categories on the given ColumnMeta list in place.
test_query	Test SQL query by fetching only one row.

types.DataSource.cleanup()

Clean up resources associated with the data source.

This method should clean up any connections or resources used by the data source.

Name	Type	Description
	None

types.DataSource.execute_query(query)

Execute SQL query and return results.

Name	Type	Description	Default
query	str	SQL query to execute	required

Name	Type	Description
	`IntoFrameT`	Query results

types.DataSource.get_column_metas()

Return column names and types without running stats queries.

types.DataSource.get_data()

Return the unfiltered data.

Name	Type	Description
	`IntoFrameT`	The complete dataset

types.DataSource.get_data_description()

Get a human-readable data description for the system prompt.

Subclasses may override this to provide metadata-derived descriptions (e.g., pin title/description). The default returns an empty string.

types.DataSource.get_db_type()

Name for the database behind the SQL execution.

types.DataSource.get_schema(categorical_threshold)

Return schema information about the table as a string.

Name	Type	Description	Default
categorical_threshold	int	Maximum number of unique values for a text column to be considered categorical	required

Name	Type	Description
	str	A string containing the schema information in a format suitable for prompting an LLM about the data structure

types.DataSource.get_semantic_views_description()

Get information about semantic views (if any) for the system prompt.

types.DataSource.populate_column_stats(columns, categorical_threshold)

Populate min/max/categories on the given ColumnMeta list in place.

types.DataSource.test_query(query, *, require_all_columns=False)

Test SQL query by fetching only one row.

Name	Type	Description	Default
query	str	SQL query to test	required
require_all_columns	bool	If True, validates that result includes all original table columns. Additional computed columns are allowed.	`False`

Name	Type	Description
	`IntoFrameT`	Query results with at most one row

Name	Type	Description
	`MissingColumnsError`	If require_all_columns is True and result is missing required columns