databricks-model-serving

What problem does it solve?

This Skill streamlines the deployment and management of machine learning models and advanced AI agents on Databricks, making them accessible via scalable REST APIs.

Core Features & Use Cases

• Model Deployment: Deploy classical ML models (sklearn, xgboost) and custom Python models (PyFunc) to production endpoints.
• AI Agent Deployment: Deploy sophisticated GenAI agents built with LangGraph and ResponsesAgent, integrating tools like UC Functions and Vector Search.
• Endpoint Management: Provides tools for querying deployed endpoints, checking their status, and managing deployments.
• Use Case: A data science team can use this Skill to deploy a trained image classification model or a customer service chatbot agent, making it available for real-time predictions or interactions.

Quick Start

Use the databricks-model-serving skill to deploy the registered MLflow model 'main.models.my_classifier' to a new serving endpoint.