Multilingual Text Analytics on Google Cloud
Composer schedules Dataflow, models translate and classify, BigQuery checks quality, Looker shows the result the next day.
A reference design for a daily text-analytics pipeline on Google Cloud. Cloud Composer runs Apache Beam jobs on Dataflow that stage text in many languages; Vertex AI, a large language model and a fine-tuned classifier translate and classify it; BigQuery is the data-quality checkpoint; Elasticsearch, Looker and applications on GKE put the results in front of people.
Point at a component to light its links; select it for what it does here and the practice that makes it right on Google Cloud. A Google Cloud product without an icon of its own shows its category's icon, as Google's icon set does.
When to use it
- Text from customers in many languages to classify every day
- Analytics that must reach stakeholders within a day
- A data team that needs DevOps, data and AI engineers together
How NGT delivers it
Built from code, reviewed at a gate by an NGT architect, and handed over with runbooks your team can run.
DataOps
