init

init(
    data_source,
    table_name,
    greeting=None,
    data_description=None,
    extra_instructions=None,
    create_chat_callback=None,
    system_prompt_override=None,
)

Initialize querychat with any compliant data source.

Parameters

Name	Type	Description	Default
data_source	IntoFrame | sqlalchemy.Engine	Either a Narwhals-compatible data frame (e.g., Polars or Pandas) or a SQLAlchemy engine containing the table to query against.	required
table_name	str	If a data_source is a data frame, a name to use to refer to the table in SQL queries (usually the variable name of the data frame, but it doesn’t have to be). If a data_source is a SQLAlchemy engine, the table_name is the name of the table in the database to query against.	required
greeting	str	A string in Markdown format, containing the initial message	None
data_description	str	Description of the data in plain text or Markdown	None
extra_instructions	str	Additional instructions for the chat model	None
create_chat_callback	CreateChatCallback	A function that creates a chat object	None
system_prompt_override	str	A custom system prompt to use instead of the default	None

Returns

Name	Type	Description
	QueryChatConfig	A QueryChatConfig object that can be passed to server()