DatabricksInstall

Overview

The "Delete Serving Endpoint" operation in the Model Serving resource allows users to delete a specified serving endpoint from Databricks. This is useful for managing and cleaning up model deployment endpoints that are no longer needed, helping to maintain an organized and cost-effective environment.

Practical scenarios include:

• Removing outdated or deprecated model endpoints.
• Cleaning up test or temporary endpoints after experimentation.
• Automating lifecycle management of model deployments in CI/CD pipelines.

Properties

Output

The node outputs a JSON object indicating the result of the deletion operation. Typically, this will contain confirmation details such as success status or any relevant messages returned by the API. There is no binary data output associated with this operation.

Example output structure (conceptual):

{
  "success": true,
  "message": "Serving endpoint deleted successfully"
}

Dependencies

• Requires an API authentication token credential to access the Databricks API.
• The node uses the base URL and authorization token from the configured credentials.
• No additional external dependencies beyond the Databricks API.

Troubleshooting

• Common Issues:

  • Providing an incorrect or non-existent endpoint name will likely cause an API error.
  • Network connectivity issues can prevent the request from reaching Databricks.
  • Insufficient permissions on the API token may result in authorization errors.

• Error Messages:

  • API Error: <status code> <status text>: Indicates the API responded with an error. Check the endpoint name and permissions.
  • Network Error: No response received from server: Suggests network problems or incorrect host configuration.
  • Other generic errors will include message and stack trace if continue-on-fail is enabled.

• Resolutions:

  • Verify the endpoint name is correct and exists.
  • Ensure the API token has sufficient privileges to delete serving endpoints.
  • Confirm network connectivity and correct host URL in credentials.
  • Enable continue-on-fail to handle errors gracefully during batch operations.

Links and References

• Databricks Model Serving API Documentation
• Databricks REST API Reference