@kapa.ai, why after sync data, Airbyte just create internal table __airbyte_raw_xxx with data in json. Cannot see a new table with data in separate columns?_

Airbyte operates on an ELT (Extract, Load, Transform) model. This means that during the data synchronization process, raw data is first loaded into a destination and then after the data has been written, it goes through a transformation stage. When Airbyte syncs data, it first loads the data into raw tables (named like

_airbyte_raw_xxx

) in the destination. The data in these raw tables is stored as JSON blobs in the

_airbyte_data

column. This is done to ensure that the raw data is always accessible and can be re-transformed in the future without the need for a resync of data from source systems [source](https://airbyte.com/tutorials/full-data-synchronization#step-1). If you have enabled [Basic Normalization](https://docs.airbyte.com/understanding-airbyte/basic-normalization/), Airbyte will create a normalized table by extracting data from the JSON object in the raw table. This normalized table will have data in separate columns. If you are not seeing the normalized tables, it could be because: - Basic Normalization is not enabled. - The destination does not support normalization. You can check the list of [destinations that support normalization](https://docs.airbyte.com/understanding-airbyte/basic-normalization#destinations-that-support-basic-normalization). - There might be an issue with the sync process. You can check the logs for any errors. If you need to query the raw data before it's normalized, some destinations like ClickHouse provide JSONExtract-functions to parse the data from the

_airbyte_data

column [source](https://github.com/airbytehq/airbyte/issues/36199).

@kapa.ai, I'm using the Azure MS SQL Server v1.0.0. Is that version having issue with normalization?

A message from kapa.ai

New message text here