databricks-model-serving

Deploy Databricks MLflow models and GenAI agents to scalable serving endpoints.

Updated Sep 9, 2017
One-click install
npx skills add https://github.com/mirakui/dotfiles --skill databricks-model-serving-mirakui
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-model-serving
Source: https://github.com/mirakui/dotfiles/tree/main/claude/skills/databricks-model-serving
Command: npx skills add https://github.com/mirakui/dotfiles --skill databricks-model-serving-mirakui

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deploy and manage scalable Databricks model-serving endpoints for MLflow models and GenAI agents, enabling consistent access, monitoring, and governance.

Core Features & Use Cases

  • Deploy traditional ML models to serving endpoints with autolog and UC integration.
  • Deploy and query GenAI agents (ResponsesAgent and LangGraph) through endpoints.
  • Integrate Unity Catalog functions and Vector Search tools to empower tool-enabled agents and complex retrieval.
  • Use cases include online inference, A/B testing, model versioning, and endpoint status checks.

Quick Start

Deploy a model to a Databricks Serving Endpoint and run a test query.

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 serving endpoints by explicitly naming the endpoint and logging the model. This enables scalable online inference and consistent access for traditional ML and custom PyFunc models.

Can I deploy LangGraph agents to Databricks serving endpoints?

Yes, you can deploy GenAI agents including ResponsesAgent and LangGraph to Databricks serving endpoints. This allows scalable querying and management of your tool-enabled agents.

How do Unity Catalog functions work with Databricks model serving?

Unity Catalog functions integrate with Databricks model serving by acting as optional resources included at MLflow log time. They empower tool-enabled GenAI agents to perform complex retrieval and integrated querying.

Does Databricks model serving support vector search tools for GenAI agents?

Yes, Databricks model serving supports vector search tools. You include vector search indexes as optional resources at MLflow log time to enable complex retrieval for deployed GenAI agents.

What are the requirements for logging GenAI agents to Databricks endpoints?

Logging GenAI agents to Databricks endpoints requires explicit endpoint naming and MLflow model logging. Optional resources like Unity Catalog functions or vector search indexes must be included at log time.