Where can you fine-tune Gemini models from your warehouse data?
Why C is the answer
BigQuery
BigQuery can fine-tune Gemini models using data held in your warehouse.
In detail
- BigQuery can fine-tune Gemini models from warehouse data.
- This keeps data in the warehouse.
Use case
An illustrative scenario, not a real incident.
A team's examples already live in BigQuery, so it fine-tunes a Gemini model from there.
See it in different ways
flowchart TD
A{"Where does the team work?"} -->|"SQL in BigQuery"| B["BigQuery ML"]
A -->|"No code, managed training"| C["Agent Platform AutoML"]
A -->|"Common task, no training needed"| D["Pre-built APIs: Document AI, Vision, Translate"]stateDiagram-v2 [*] --> Prompting Prompting --> Rag: lacks current facts Prompting --> FineTuning: quality or format is not reached Prompting --> Done: meets the need Rag --> Done FineTuning --> Done
flowchart LR S0["Examples in BigQuery"] --> S1["Fine-tune Gemini"] --> S2["Evaluate"]
Key point: BigQuery can fine-tune Gemini.
Why the other options are wrong
- A. Cloud SQL
- Cloud SQL is a relational database.
- B. Dataplex
- Dataplex governs data.
- D. Looker
- Looker builds reports.