Ingesting Metadata from Superset BI System with Microsoft Azure AD Authentication

Original Slack Thread

Ton wants to ingestion metadata from the Superset BI system, such as charts, datasets, and dashboards. However, our Superset system requires AUTH_OAUTH via Microsoft Azure AD.
Do you have any alternative methods, such as using a GUEST API connection, to ingestion data without going through AUTH_OAUTH? If so, could you provide guidance on how to achieve this?

Hey there! :wave:

<@U06TM7M40RK> Can you help with the questions in this thread?

:information_source: Please continue to tag RunLLM (e.g <@U06TM7M40RK>) to have it continue generating responses!

It seems likely that DataHub’s current Superset ingestion connector primarily supports basic authentication methods like username and password, and OAuth support is not explicitly mentioned in the available documentation or codebase. However, there are some potential workarounds you might consider:

  1. Custom Scripts: Some users have created custom scripts to handle OAuth authentication and then use the DataHub ingestion APIs to push metadata. This approach would require some development effort to implement the OAuth flow and obtain the necessary tokens.

  2. Proxy Authentication: Another approach is to use a proxy service that handles OAuth authentication and forwards requests to Superset with the necessary tokens. This can simplify the process by offloading the authentication complexity to a separate service.

  3. Admin User with API Access: If your Superset instance allows it, you might be able to use an admin user with API access to bypass OAuth for API calls. This would involve resetting the admin user’s password and using it for API authentication, as mentioned in a <Slack discussion>.

  4. Feature Request: If these options are not feasible, you might consider submitting a feature request to the DataHub project to support OAuth authentication for Superset ingestion. This has been discussed in the community, and there is interest in adding this feature in the future.

Would you like more detailed steps or further assistance on any specific part of the process?

Sources:

Hi, how did my answer work out for you? Need any more assistance? You can also tag <@U07FV3UHE4D> to let your fellow community members know you’re still looking for guidance.

Hi :slight_smile: ! Did this interaction resolve your issue or do you still require assistance ?

Please tag @ RunLLM if you still need further assistance !

Or tag @Datahub Community Support if you require a person to take a look :slight_smile:

Hope this helps ! ><