databricks-solutions Databricks Genie
Create and query Databricks Genie Spaces - natural language interfaces for SQL-based data exploration.
Overview
Genie Spaces allow users to ask natural language questions about structured data in Unity Catalog. The system translates questions into SQL queries, executes them on a SQL warehouse, and presents results conversationally.
When to Use This Skill
Use this skill when:
- Creating a new Genie Space for data exploration
- Adding sample questions to guide users
- Connecting Unity Catalog tables to a conversational interface
- Asking questions to a Genie Space programmatically (Conversation API)
MCP Tools
Space Management
| Tool | Purpose |
|---|---|
create_or_update_genie |
Create or update a Genie Space |
get_genie |
Get space details (by ID) or list all spaces (no ID) |
delete_genie |
Delete a Genie Space |
Conversation API
| Tool | Purpose |
|---|---|
ask_genie |
Ask a question or follow-up (conversation_id optional) |
Supporting Tools
| Tool | Purpose |
|---|---|
get_table_details |
Inspect table schemas before creating a space |
execute_sql |
Test SQL queries directly |
Quick Start
1. Inspect Your Tables
Before creating a Genie Space, understand your data:
get_table_details(
catalog="my_catalog",
schema="sales",
table_stat_level="SIMPLE"
)
2. Create the Genie Space
create_or_update_genie(
display_name="Sales Analytics",
table_identifiers=[
"my_catalog.sales.customers",
"my_catalog.sales.orders"
],
description="Explore sales data with natural language",
sample_questions=[
"What were total sales last month?",
"Who are our top 10 customers?"
]
)
3. Ask Questions (Conversation API)
ask_genie(
space_id="your_space_id",
question="What were total sales last month?"
)
# Returns: SQL, columns, data, row_count
Workflow
1. Inspect tables → get_table_details
2. Create space → create_or_update_genie
3. Query space → ask_genie (or test in Databricks UI)
4. Curate (optional) → Use Databricks UI to add instructions
Reference Files
- spaces.md - Creating and managing Genie Spaces
- conversation.md - Asking questions via the Conversation API
Prerequisites
Before creating a Genie Space:
- Tables in Unity Catalog - Bronze/silver/gold tables with the data
- SQL Warehouse - A warehouse to execute queries (auto-detected if not specified)
Creating Tables
Use these skills in sequence:
databricks-synthetic-data-gen- Generate raw parquet filesdatabricks-spark-declarative-pipelines- Create bronze/silver/gold tables
Common Issues
| Issue | Solution |
|---|---|
| No warehouse available | Create a SQL warehouse or provide warehouse_id explicitly |
| Poor query generation | Add instructions and sample questions that reference actual column names |
| Slow queries | Ensure warehouse is running; use OPTIMIZE on tables |
Related Skills
- databricks-agent-bricks - Use Genie Spaces as agents inside Supervisor Agents
- databricks-synthetic-data-gen - Generate raw parquet data to populate tables for Genie
- databricks-spark-declarative-pipelines - Build bronze/silver/gold tables consumed by Genie Spaces
- databricks-unity-catalog - Manage the catalogs, schemas, and tables Genie queries