Train your AI on Snowflake
Connect your Snowflake data warehouse to train your AI agent on structured business data. Open syncs tables and views, making your data warehouse knowledge accessible to your AI agent.
Connect once, and Open automatically keeps your AI agent's knowledge up to date. When you update content in Snowflake, the changes sync automatically—no manual retraining required.
→syncs to→AI AgentWhat can be synced
Tables — Full table data with all columns and rows.
Views — Materialized and regular views with their computed data.
Schemas — Schema metadata for structure understanding.
Features
- •Table Sync — Sync tables and views from your Snowflake database.
- •Schema Discovery — Automatic schema detection for all data types.
- •Query Filtering — Optionally filter data using SQL WHERE clauses.
- •Role-based Access — Respect Snowflake roles and access controls.
Requirements
- •Snowflake account identifier
- •User credentials with SELECT permissions
- •Warehouse, database, and schema names
- •Network access (may need to whitelist IPs)
How to connect
- 1.Create a Snowflake user with read access to required schemas
- 2.Note your account identifier, warehouse, database, and schema
- 3.In Open, go to AI Training → Sources → Connect Snowflake
- 4.Enter your Snowflake credentials and connection details
- 5.Select tables and views to sync
- 6.Configure sync frequency
Good to know
- Large tables may take significant time for initial sync
- Consider using views to filter/aggregate data before syncing
- Warehouse must be running for sync to work
- Incremental sync uses standard CDC patterns
Common questions
Security: Open only requires read access to your Snowflake. We never write, modify, or delete your content. All data is encrypted in transit and at rest. GDPR compliant, working toward SOC 2 Type II.
Ready to connect Snowflake?
AI Training → Sources → Snowflake
Other training sources
