Skip to main content

Serving Supervised ML Models

Predibase supports the serving of custom (non-LLM) models for real-time inference.

Via the SDK

Once you're satisfied with your model's performance, you can deploy it to a REST API endpoint using the create_deployment method:

rotten_tomatoes_deployment = pc.create_deployment('rotten_tomatoes_deployment', rotten_tomatoes_model)

Now that you've deployed your model, you can easily make predictions using the Deployment.predict method:

preds_df = rotten_tomatoes_deployment[0].predict(rotten_tomatoes_df.sample(100), stream=True)

With this command, you can pass in any unseen data that you want predictions on, and Predibase will return a dataframe with the predictions for each example.

Via the UI

Learn how to create a supervised ML (non-LLM) deployment in the Predibase UI.