Zero-Shot Machine Learning in SQL: Predictions Without a Training Loop
· 14 min read
You have 120 labelled rows and 30 unlabelled ones. The classical answer is a Python project. The new answer is one SELECT.
SELECT * FROM tabfm_classify('iris', 'species');
No training loop. No feature engineering. No model artifact to version. The model reads your labelled rows as context and predicts the rest—the same way an LLM learns from examples in a prompt.