A Lazyframe is an abstraction of a dataframe that can stream your data from your sync output, apply relevant transformations, and then writes to your export format without ever loading the entire dataset into memory.
import gluestick as gsimport polars as plreader = gs.PLLazyFrameReader()TENANT_ID = "TENANT_123"for stream in reader.input_files.keys(): lf = reader.get(stream, catalog_types=True) lf = lf.with_columns( pl.lit(TENANT_ID).alias("tenant_id") ) gs.to_export(lf, stream, "./etl-output", keys=["id"])
