You need text from scanned invoices, with no custom model. What fits?
Why D is the answer
Document AI API
Pre-built APIs solve common tasks without training.
In detail
- Document AI reads scanned documents with no custom model.
- Try pre-built APIs first.
Use case
An illustrative scenario, not a real incident.
An accounts team needs text from invoices, and Document AI gives it with no training.
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 [*] --> Task Task --> PrebuiltApi: a common task Task --> BigQueryMl: data in BigQuery, SQL team Task --> AutoML: custom model, no code Task --> CustomTraining: your own code
flowchart TD
Q{"Is it a common task?"}
Q -->|"Yes"| A0["Pre-built API"]
Q -->|"No"| A1["Custom model"]Key point: Pre-built APIs solve common tasks.
Why the other options are wrong
- A. A custom DNN trained on GKE from scratch
- A custom network is unnecessary.
- B. Ray on Gemini Enterprise Agent Platform with a new cluster
- A Ray cluster is unnecessary.
- C. A forecasting model built in BigQuery ML
- Forecasting does not read documents.