An inference API on the Build Your Own AI Platform track. Inference is a request with features in and a prediction out. The API authenticates, validates the schema, calls a version, and logs the version id.
This lesson assumes you already worked through Training jobs.
The idea in practice
Timeouts and payload limits are part of the API. Return a structured error, not a stack trace.
A concrete check
goal = {
'track': 'Build Your Own AI Platform',
'lesson': 'An inference API',
}
checks = [
'input available at decision time',
'score matches the real decision',
'failure case written down',
]
print(goal['lesson'])
for item in checks:
print('-', item)
Run the sketch locally if you have Python. The printout is a reminder of the checks, not a trained model. Replace the strings with the real inputs from your own example before you treat it as a design.
What usually goes wrong
An endpoint that loads a new pickle from disk on every call with no version. When this happens, stop adding parameters or tools. Fix the check, the data, or the permission, then run the same example again.
What to write down
- The input you are allowed to use at decision time.
- The output and the score or pass rule.
- One failure you will test on purpose.
- What you will not claim the system can do.
Practice
Sketch request, response, and the version field you log.
Self-check
- Say An inference API in one sentence that mentions an input and an output.
- Name the failure mode in this lesson and the check that would catch it.
Done when: you can explain this lesson without the page open, and you have a written failure case.