Actions35
- Genie Actions
- Databricks SQL Actions
- Unity Catalog Actions
- Model Serving Actions
- Files Actions
- Vector Search Actions
Overview
The node provides integration with the Databricks API, specifically enabling operations related to "Model Serving" among other resources. For the "Create Serving Endpoint" operation under the "Model Serving" resource, it allows users to create an endpoint that serves machine learning models. This is useful for deploying models in production environments where real-time inference or batch predictions are required.
Typical use cases include:
- Deploying one or more ML models behind a RESTful endpoint.
- Configuring traffic routing between multiple served models for A/B testing or gradual rollouts.
- Managing model serving infrastructure programmatically within n8n workflows.
For example, a data scientist could automate the deployment of new model versions by creating or updating serving endpoints directly from their workflow automation.
Properties
| Name | Meaning |
|---|---|
| Served Models | List of models to serve, provided as a JSON array describing each model's details. |
| Traffic Config | Traffic configuration for the endpoint, specified as a JSON object defining routing rules. |
These properties must be provided in JSON format and are required when creating or updating a serving endpoint.
Output
The node outputs JSON data representing the response from the Databricks API after creating the serving endpoint. This typically includes details about the newly created endpoint such as its ID, status, URL, and configuration.
If the node supports binary data output (not evident from the provided code), it would represent any binary payloads returned by the API, but this is unlikely for this operation.
Dependencies
- Requires an active Databricks account with appropriate permissions to manage model serving endpoints.
- Needs an API authentication token (API key or bearer token) configured in n8n credentials to authorize requests.
- The base URL for the Databricks workspace must be set in the credentials.
Troubleshooting
- Invalid JSON input: Since "Served Models" and "Traffic Config" require JSON input, malformed JSON will cause errors. Validate JSON syntax before running.
- Authentication errors: Ensure the API token is valid and has sufficient privileges.
- API endpoint errors: If the Databricks service is unreachable or returns errors, verify network connectivity and API limits.
- Missing required fields: Both properties are mandatory; omitting them will result in validation errors.