databricks-model-serving

Deploy MLflow models and AI agents to Databricks Model Serving endpoints.

Updated Mar 12, 2026
One-click install
npx skills add https://github.com/juanlamadrid20/coda --skill databricks-model-serving-juanlamadrid20
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-model-serving
Source: https://github.com/juanlamadrid20/coda/tree/main/.claude/skills/databricks-model-serving
Command: npx skills add https://github.com/juanlamadrid20/coda --skill databricks-model-serving-juanlamadrid20

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), custom PyFunc models, and GenAI agents (ResponsesAgent, LangGraph) to production endpoints.
  • Endpoint Querying: Interact with deployed models and agents using Python SDK, REST API, or MCP tools.
  • Tool Integration: Seamlessly integrate Unity Catalog Functions and Vector Search indexes into AI agents.
  • Use Case: Deploy a customer churn prediction model as a serving endpoint and then query it from a business intelligence dashboard to identify at-risk customers in real-time.

Quick Start

Use the databricks-model-serving skill to deploy the 'main.models.my_classifier' model version 1 to a serving endpoint named 'my-classifier-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?

Deploy MLflow models to Databricks Model Serving by configuring scalable REST API endpoints. This process supports classical ML, custom PyFunc, and GenAI agents for real-time inference and application integration.

Can I deploy AI agents like LangGraph to Databricks endpoints?

Deploy GenAI agents including LangGraph and ResponsesAgent to Databricks Model Serving. These deployed agents can then be queried using the Python SDK, REST API, or MCP tools.

Does Databricks Model Serving integrate with Unity Catalog Functions and Vector Search?

Databricks Model Serving supports direct integration with Unity Catalog Functions and Vector Search indexes. This allows you to seamlessly incorporate these tools into your deployed AI agents.

How do I query a deployed model from a business intelligence dashboard?

Query deployed models from a business intelligence dashboard by interacting with the Databricks Model Serving endpoint using the Python SDK or REST API. This enables real-time inference for applications.

What types of machine learning models are supported for endpoint deployment?

Endpoint deployment supports classical ML models like sklearn and xgboost, custom PyFunc models, and GenAI agents. This provides flexible REST API access for various production inference needs.