ai_parse_document
https://www.databricks.com/blog/arrow-optimized-python-udfs-apache-sparktm-35
https://www.databricks.com/blog/announcing-automatic-liquid-clustering
@pandas_udf decorator
.cache() - MEM .persist() - MEM/DISK
"_metadata.file_name"
CLUSTER BY AUTO
%sql SELECT LABUSER 3434141241