Data Source Base Class — DataSource • querychat

An abstract R6 class defining the interface that custom QueryChat data sources must implement. This class should not be instantiated directly; instead, use one of its concrete implementations like DataFrameSource or DBISource.

Public fields

table_name: Name of the table to be used in SQL queries

Methods

`DataSource$get_db_type()`

Get the database type

Usage

DataSource$get_db_type()

Returns

A string describing the database type (e.g., "DuckDB", "SQLite")

`DataSource$get_schema()`

Get schema information about the table

Usage

DataSource$get_schema(categorical_threshold = 20, table_spec = NULL)

Arguments

categorical_threshold: Maximum number of unique values for a text column to be considered categorical

Returns

A string containing schema information formatted for LLM prompts

`DataSource$get_schema_result()`

Usage

DataSource$get_schema_result(categorical_threshold = 20, table_spec = NULL)

`DataSource$execute_query()`

Execute a SQL query and return results

Usage

DataSource$execute_query(query)

Arguments

query: SQL query string to execute

Returns

A data frame containing query results

`DataSource$test_query()`

Test a SQL query by fetching only one row

Usage

DataSource$test_query(query, require_all_columns = FALSE)

Arguments

query: SQL query string to test
require_all_columns: If TRUE, validates that the result includes all original table columns (default: FALSE)

Returns

A data frame containing one row of results (or empty if no matches)

`DataSource$get_data()`

Get the unfiltered data as a data frame

Usage

DataSource$get_data()

Returns

A data frame containing all data from the table

`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.

Usage

DataSource$get_data_description()

Returns

A string, or empty string if no description is available.

`DataSource$cleanup()`

Release resources this data source created. Only resources querychat opened itself are closed (for example the in-memory DuckDB connection a DataFrameSource creates). Connections passed in by the caller are never closed; their lifecycle stays with the caller.

Usage

DataSource$cleanup()

Returns

NULL (invisibly)

`DataSource$clone()`

The objects of this class are cloneable with this method.

Usage

DataSource$clone(deep = FALSE)

Arguments

deep: Whether to make a deep clone.

Examples

MyDataSource <- R6::R6Class(
  "MyDataSource",
  inherit = DataSource,
  public = list(
    initialize = function(table_name) {
      self$table_name <- table_name
    }
    # Implement abstract methods here...
  )
)