Extract Structured JSON Data from Unstructured Data using Databricks Mosaic AI > Using the Extract Structured JSON Data from Unstructured Data using Databricks Mosaic AI recipe > Step 3. Configure and publish the processes
  

Step 3. Configure and publish the processes

Configure the name of the serving endpoint in Databricks Mosaic AI and publish the processes.
  1. 1To publish the Get Content from File process, click Actions in the row that contains the process and select Publish.
  2. 2Open the Extract Structured Data from Unstructured Data process.
  3. 3On the Temp Fields tab of the Start step, enter the name of the serving endpoint in Databricks Mosaic AI in the ServingEndPointName field. Default is databricks-meta-llama-3-1-8b-instruct. You can optionally edit the serving endpoint name.
  4. 4Save and publish the process.