update doc

template/{{.input_root_dir}}/docs/mlops-setup.md.tmpl

@@ -334,12 +334,14 @@ Add the following [Gitlab CI/CD variables](https://docs.gitlab.com/ee/ci/variabl
 Ensure that the variable visibility is set to masked and hidden.
 
 ### Building and Pushing the Docker image
-Gitlab exectues the pipeline on a VM that you can configure to be initialized from a Docker image.
+Gitlab exectues the pipeline on a VM initialized from a Docker image.
+The default Docker image is: [databricksfieldeng/mlopsstack:latest](https://hub.docker.com/repository/docker/databricksfieldeng/mlopsstack/general). 
 The Docker image should include all requirements to run the CI/CD pipelines (e.g. Databricks CLI, Python and its libraries used in the unit tests, Java for executing spark locally to the VM).
 The folder `.gitlab/docker/` includes the files to build the Docker image.  
-You can execute the following script to locally build and push the docker image into a registry:  
+
+You can execute the following script to locally build and push the Docker image into a registry on your local machine:  
 `{{.input_root_dir}}/.gitlab/docker/push_image_to_gitlab.sh`  
-You can execute the script to build and push the image on your local machine. Once executed, make sure that each pipeline yml file
+Make sure that each pipeline yml file
 (in the folder `.gitlab/pipelines/`) points to that image.  
 NOTE: you can use the same image for multiple projects. 
 If a project requires additional Python libraries, they can also be installed as part of the pipelines scripts.