databricks-model-serving

Deploy and query Databricks model-serving endpoints for ML models and AI agents.

1|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/leary-poken/ai-dev-kit --skill databricks-model-serving-leary-poken
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-model-serving
Source: https://github.com/leary-poken/ai-dev-kit/tree/main/databricks-skills/databricks-model-serving
Command: npx skills add https://github.com/leary-poken/ai-dev-kit --skill databricks-model-serving-leary-poken

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deploy and query Databricks model-serving endpoints for ML models and AI agents in a scalable, managed way.

Core Features & Use Cases

  • Deploy traditional ML models (e.g., sklearn, xgboost) to serving endpoints and auto-log with MLflow.
  • Deploy GenAI agents (ResponsesAgent/LangGraph) to endpoints and perform live querying and tool-based interactions.
  • Integrate Unity Catalog Functions or Vector Search tools to enable tool calls and retrieval within endpoints.
  • Query endpoints, check status, and validate deployments via SDK, REST, or MCP tooling in production.

Quick Start

Deploy a model or GenAI agent to a Databricks model-serving endpoint and run a test query to verify the deployment.

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 a machine learning model to a Databricks model-serving endpoint?

Deploy traditional ML models like sklearn or xgboost to Databricks model-serving endpoints and auto-log them with MLflow for scalable, managed serving in production.

Can I deploy GenAI agents to Databricks serving endpoints and perform live querying?

Deploy GenAI agents like ResponsesAgent or LangGraph to Databricks model-serving endpoints to perform live querying and tool-based interactions in production environments.

How do I integrate Unity Catalog Functions or Vector Search tools with model-serving endpoints?

Integrate Unity Catalog Functions or Vector Search tools with Databricks model-serving endpoints to enable tool calls and retrieval actions directly within your deployed models and AI agents.

What's the best way to check the status and validate a Databricks model-serving endpoint deployment?

Check endpoint status and validate Databricks model-serving deployments via SDK, REST, or MCP tooling to ensure robust validation of inputs and responses in production.

Do I need exact endpoint names and MLflow integration to query Databricks model-serving endpoints?

Querying Databricks model-serving endpoints requires exact endpoint names from SKILL.md, MLflow and Unity Catalog integration, and robust validation of inputs and responses for successful deployment.