model-serving

Name: model-serving
Availability: InStock
Author: databricks-solutions

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

1.8k|404|Updated Dec 17, 2025

Search Tags:#agents #MLflow #deploy #endpoints #model-serving #Databricks #Unity Catalog

Ready to run

npx skills add https://github.com/databricks-solutions/ai-dev-kit --skill model-serving

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-serving
Source: https://github.com/databricks-solutions/ai-dev-kit/tree/main/databricks-skills/model-serving
Command: npx skills add https://github.com/databricks-solutions/ai-dev-kit --skill model-serving

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables teams to deploy MLflow models and AI agents to scalable Databricks Model Serving endpoints and to query them reliably.

Core Features & Use Cases

Deploy traditional ML models (sklearn, xgboost) and custom PyFunc models to serving endpoints.
Deploy GenAI agents (ResponsesAgent) and LangGraph-based agents with tool-calling capabilities.
Query endpoints, check endpoint status, and monitor deployments across development, staging, and production.

Quick Start

Install required packages and authentication for Databricks, then log a model, deploy it to a serving endpoint, and start querying the endpoint. Typical steps include installing mlflow, databricks-langchain, langgraph, databricks-agents, and pydantic; logging the model with MLflow; deploying via Databricks UI or API; and sending requests to the endpoint to receive predictions.

Frequently Asked Questions about 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 logging the model with MLflow autolog or pyfunc, then using the Databricks API or UI to create scalable endpoints for querying predictions.

Can I deploy GenAI agents with tool-calling capabilities to Databricks endpoints?▼

Yes, you can deploy GenAI agents to Databricks endpoints. The skill supports deploying ResponsesAgent and LangGraph-based agents with tool-calling capabilities to scalable serving endpoints.

Does Databricks Model Serving support Unity Catalog integration for deployed models?▼

Databricks Model Serving supports Unity Catalog integration, allowing you to manage permissions and govern access to deployed ML models and GenAI agents through Unity Catalog.

How do I check the status of a Databricks model serving endpoint?▼

Check Databricks model serving endpoint status using the built-in query and monitoring functions to verify deployment progress across development, staging, and production environments.

Do I need permissions to create and query Databricks serving endpoints?▼

Yes, creating and querying Databricks serving endpoints requires explicit permissions. You need authorization to create endpoints and send requests to retrieve predictions from deployed MLflow models and agents.

What packages are required to deploy models and agents to Databricks serving endpoints?▼

Required packages include mlflow, databricks-langchain, langgraph, databricks-agents, and pydantic, along with Databricks authentication setup to deploy and query serving endpoints.