Train your AI on BigQuery
Connect your Google BigQuery data warehouse to train your AI agent on analytics data. Open syncs tables and views, bringing your structured business intelligence data to your AI agent.
Connect once, and Open automatically keeps your AI agent's knowledge up to date. When you update content in BigQuery, the changes sync automatically—no manual retraining required.
→syncs to→AI AgentWhat can be synced
Tables — Full table data including all columns and nested/repeated fields.
Views — Materialized views with their computed data.
Nested Data — Support for STRUCT and ARRAY column types.
Features
- •Dataset Sync — Sync tables from selected BigQuery datasets.
- •Partitioned Tables — Support for partitioned tables with efficient incremental sync.
- •View Support — Sync both tables and materialized views.
- •GCP Integration — Native Google Cloud authentication with service accounts.
Requirements
- •GCP service account with BigQuery Data Viewer role
- •Service account JSON key file
- •Project ID and dataset names
How to connect
- 1.Create a GCP service account with BigQuery Data Viewer role
- 2.Generate and download a JSON key for the service account
- 3.In Open, go to AI Training → Sources → Connect BigQuery
- 4.Upload your service account JSON key
- 5.Enter your GCP project ID and dataset names
- 6.Select tables to sync
Good to know
- Costs may apply for BigQuery data scanned during sync
- Large tables benefit from partitioning for incremental sync
- Nested and repeated fields are flattened in the output
- Consider using views to pre-aggregate data
Common questions
Security: Open only requires read access to your BigQuery. 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 BigQuery?
AI Training → Sources → BigQuery
Other training sources
