Databricks has introduced new functionality for serving machine learning models through a serverless REST API, enabling the consumption of models outside of Databricks. While serving the model via REST API is ideal for external use cases, it is recommended to use the distributed UDF function within Spark Databricks for optimal performance when serving the model internally. With these options, you can now seamlessly serve your machine-learning models inside and outside Databricks. https://docs.databricks.com/machine-learning/model-inference/serverless/serverless-real-time-inferen...
