Getting started

Prior to starting modeling workflows, ensure you have a high-level understanding of core Foundry concepts, Code Repositories, Python transforms, Ontology, and Functions.

If you are new to Foundry, the supervised learning tutorial provides a walkthrough from setting up a new project to deploying a model into production.

Common model creation workflows

• Train a model with data from the Palantir platform in a Jupyter® code workspace or code repository
• Import model weights and register them as a model
• Import and register a container as a model
• Register an externally hosted model

Deploying a model for inference and consumption

• Deploying a model using Foundry ML Live
• Using a model as an input to Python transforms
• Evaluating model performance
• Using a model “deployment” for batch inference

Registering a model for use in the Ontology

• Register a Live deployment for use in Typescript functions
• Register a model to be used directly as a function in the Ontology