databricks-genie

Create and query Databricks Genie Spaces for natural language SQL exploration.

1.8k|404|Updated Dec 17, 2025
One-click install
npx skills add https://github.com/databricks-solutions/ai-dev-kit --skill databricks-genie
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-genie
Source: https://github.com/databricks-solutions/ai-dev-kit/tree/main/databricks-skills/databricks-genie
Command: npx skills add https://github.com/databricks-solutions/ai-dev-kit --skill databricks-genie

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Databricks Genie Spaces empower teams to translate natural language questions into SQL, enabling consistent, curated data access across Unity Catalog without manual coding.

Core Features & Use Cases

  • Space management: Create, update, list, and delete Genie Spaces to organize data conversations.
  • Conversation API: Ask questions and get SQL-generated results within a guided space.
  • Reference-ready docs: Use provided reference files to curate space prompts and sample questions for faster onboarding.

Quick Start

Create a Genie Space with display_name "Sales Analytics" and table_identifiers ["my_catalog.sales.customers","my_catalog.sales.orders"]. Then try a question via the Conversation API: ask_genie(space_id, "What were total sales last month?")

Frequently Asked Questions about databricks-genie

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

FAQPage Schema
How do I query Databricks Unity Catalog tables using natural language instead of writing SQL manually?

You can query Unity Catalog tables using natural language by creating a Genie Space with your target table identifiers and asking questions through the Conversation API. The space translates your natural language questions into SQL queries automatically.

What do I need to set up before creating a Genie Space for natural language data exploration?

Creating a Genie Space requires access to Unity Catalog metadata to define table identifiers and a configured SQL warehouse to process the natural language queries generated by the Genie Conversation API.

How do I manage and organize Genie Spaces for different data analytics workflows?

You can manage Genie Spaces using supported workflows to create, update, list, and delete spaces. This allows you to organize data conversations and curate specific table access for different analytics use cases.

Can I ask follow-up questions in a Databricks Genie Space conversation?

Yes, you can ask follow-up questions using the ask_genie_followup function within the Conversation API. This allows you to continue exploring data and refining SQL query results within an existing Genie Space context.

What is the best way to curate prompts and sample questions for a new Genie Space?

The best way to curate prompts and sample questions is by using the provided reference files. These references help guide the Genie Space behavior and accelerate onboarding for natural language SQL exploration.