Custom model serving using Databricks Asset Bundles

MLOperator — Mon, 17 Mar 2025 21:49:38 GMT

I am using MLFlow to register custom model (python model) in Unity Catalog, and Databricks Asset Bundle to create a serving endpoint for that custom model.
I was able to create the serving endpoint using DABs, but I want to deploy the model by using custom alias instead of the entity_version.

Is it possible to create a serving endpoint of a registered model by alias using DABs?
I want something like this to define the entity_name: 'myCatalog.mySchema.my-ads-model@myAlias'

Bundle sample

bundle: name: model_bundle resources: model_serving_endpoints: uc_model_serving_endpoint: name: 'uc-model-endpoint' config: served_entities: - entity_name: 'myCatalog.mySchema.my-ads-model' entity_version: '10' workload_size: 'Small' scale_to_zero_enabled: 'true' traffic_config: routes: - served_model_name: 'my-ads-model-10' traffic_percentage: '100' tags: - key: 'team' value: 'data science'

Re: Custom model serving using Databricks Asset Bundles

koji_kawamura — Tue, 18 Mar 2025 05:22:08 GMT

Hi @MLOperator

Since model_serving_endpoints only accepts a version number of a served entity, I think that is not possible. However, the get-by-alias version API can be used to retrieve a version number from a model alias name. Then the model name and its version can be passed as variables.

As an example, I tested the following configuration:

variables:
  model_name:
  model_champion_version:

resources:
  model_serving_endpoints:
    uc_model_serving_endpoint:
      name: 'labuser9602087_1742260663_test'
      config:
        served_entities:
          - entity_name: '${var.model_name}'
            entity_version: '${var.model_champion_version}'
            workload_size: 'Small'
            scale_to_zero_enabled: 'true'
      tags:
        - key: 'team'
          value: 'data science'

When deploying it, the variables can be assigned like below. I'm using "champion" as the alias name:

export BUNDLE_VAR_model_name="catalog_name.schema_name.model_name"
export BUNDLE_VAR_model_champion_version=`databricks model-versions get-by-alias $BUNDLE_VAR_model_name champion |grep '"version":' |sed -r 's/.+:(.+)/\1/'`
databricks bundle deploy

Not ideal, but it worked. I hope this helps!

topic Re: Custom model serving using Databricks Asset Bundles in Machine Learning

Custom model serving using Databricks Asset Bundles

Re: Custom model serving using Databricks Asset Bundles