Serving Preflight and Regress

Serving Preflight and Regress

Check model status, read the signature, then run regression inference.

1. Confirm the ModelServer has the model loaded and reports a version in the AVAILABLE state before any inference is attempted.
2. Read the metadata of the latest available version to confirm the model exposes a regression signature and to see the features it expects.
3. Submit the examples for regression against the model's latest available version, returning the predicted numeric value for each example.

What you'll need to have ready

• modelName: The name the model was registered under in the ModelServer.
• signatureName: Optional regression signature to target. When omitted the ModelServer uses the model's default serving signature.
• context: Optional context features shared across every supplied example.
• examples: The tf.Example style input records to score, one numeric result returned per example.

For your developer

Arazzo workflow tensorflow:regress-preflight, 3 operations: getModelStatus → getModelMetadata → regressModel. Specs on APIs.io.