Can you deploy models that can be queried/called/inferred outside your organization?

[SeanB]

It looks like you can via MLflow but I wanted to check before diving deeper?

Also it seems like if it is possible, it's just for small scale experimentation?

Thank you!

[Kaniz]

Hi @ SeanB ! My name is Kaniz, and I'm the technical moderator here. Great to meet you, and thanks for your question! Let's see if your peers in the community have an answer to your question first. Or else I will get back to you soon. Thanks.

[Atanu]

@Sean B​  just wanted to check from where actually you are trying to query ?

[Atanu]

Means - outside databricks

[SeanB]

Yes, outside databricks.

[SeanB]

Yes, If somebody outside Databricks can query/use a model built in Databricks. I assume the answer must be yes?

[Kaniz · Accepted solution]

Hi @Sean B​ , Model access rights are inherited from the Model Registry. Enabling or disabling the serving feature requires ‘manage’ permission on the registered model. Anyone with read rights can score any of the deployed versions. (Source)