← MLOps basics
Lesson 1 of 3
Deploying models
Watch, read the card, then practise. Model serving · APIs for models
The video for this lesson is being recorded.
Meanwhile, the notes below and the 60-second cards cover the same ideas.
Practise this topicModel serving
Serving a model means running it so other systems can send inputs and get predictions.
Remember: Watch p95 latency, not just the average.
APIs for models
A model API takes input as JSON over HTTP, checks it, and returns the prediction as JSON.
Remember: Reject bad input with a clear error, never a silent guess.
Try the example in Code Lab
times = sorted([80, 85, 88, 90, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 105, 110, 115, 120, 250, 300]) print(times[18], "ms p95")