databricks-model-serving

Deploy and query MLflow models and AI agents on Databricks Model Serving.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/slysik/databricks-claude-coding --skill databricks-model-serving-slysik
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-model-serving
Source: https://github.com/slysik/databricks-claude-coding/tree/main/.claude/skills/databricks-model-serving
Command: npx skills add https://github.com/slysik/databricks-claude-coding --skill databricks-model-serving-slysik

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the deployment and querying of machine learning models and AI agents on Databricks, enabling scalable REST API access for various applications.

Core Features & Use Cases

  • Model Deployment: Deploy classical ML models (sklearn, xgboost) and custom Python models (PyFunc) to production endpoints.
  • GenAI Agent Deployment: Build, log, and deploy sophisticated AI agents using ResponsesAgent and LangGraph, integrating with foundation models and tools.
  • Tool Integration: Seamlessly incorporate Unity Catalog Functions and Vector Search indexes as tools for your agents.
  • Endpoint Querying: Interact with deployed models and agents via SDKs, REST APIs, or MCP tools.
  • Use Case: Deploy a customer churn prediction model for real-time scoring or launch a conversational AI assistant that leverages internal knowledge bases and performs actions via UC Functions.

Quick Start

Use the databricks-model-serving skill to deploy the 'main.agents.my_agent' model version 1 to a serving endpoint.

Frequently Asked Questions about databricks-model-serving

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy MLflow models to Databricks Model Serving endpoints?

You can deploy MLflow models to Databricks Model Serving by logging your model or agent and then configuring a serving endpoint for scalable REST API access.

Can I deploy GenAI agents with LangGraph on Databricks?

Yes, you can deploy GenAI agents using LangGraph on Databricks. The skill supports building, logging, and deploying sophisticated agents using ResponsesAgent and LangGraph integrated with foundation models.

Does Databricks Model Serving support Unity Catalog Functions as agent tools?

Yes, Databricks Model Serving supports Unity Catalog Functions as agent tools. You can seamlessly incorporate these functions and Vector Search indexes into your deployed GenAI agents.

What is the best way to query deployed models on a Databricks serving endpoint?

The best way to query deployed models on a Databricks serving endpoint is via SDKs, REST APIs, or MCP tools. This enables direct interaction with your production models and agents.

How do I expose a custom Python PyFunc model as a REST API?

To expose a custom Python PyFunc model as a REST API, use the skill to deploy it to Databricks Model Serving, which handles creating a scalable API endpoint for real-time scoring.

Can I use Databricks Vector Search indexes as tools for my AI agents?

Yes, you can use Databricks Vector Search indexes as tools for your AI agents. The skill enables seamless integration of these indexes alongside Unity Catalog Functions during agent deployment.