Creating a Datasource in DKubeX

This tutorial guides you through the process of creating (or adding, to be more clear) a datasource in DKubeX. A datasource is essential for storing and managing datasets that will be used for training and evaluating machine learning models.

• On the DKubeX UI, navigate to the Datasources tab from the left sidebar. The datasources page will open, displaying a list of existing connected datasources (if any).

  

  DKubeX Datasources page

• Click on the + button, which is the datasource create button, located in the top-left corner of the datasources page. This will open the Datasource Create page.

  

  DKubeX Datasource Create Button

• In the Datasource Create page, provide a unique name for the datasource to be added, and select the source type from the Source dropdown provided. In DKubeX, you can add datasources from the following source types:

  • NFS

  • S3 (AWS or AWS-like)

  • Snowflake

NFSS3 (AWS or AWS-like)Snowflake

DKubeX NFS Datasource Create page

In case of NFS datasource, provide the following details:

NFS Datasource Details

Field	Description
Server	The NFS server address.
Path	The path on the NFS server where the data is stored.

• After providing all the necessary details for the selected datasource type, click on the Create button located at the bottom-right corner of the Datasource Create page. This will add the datasource to DKubeX and allow you to use this in your MLOps workflows.