Skip to content

Calling a hosted Google language model straight from BigQuery

BigQuery lets you call Google's pretrained large language models directly from SQL by creating a remote model object that points to a Vertex AI endpoint through a BigQuery Cloud resource connection. This enables generative AI tasks like text generation and embeddings without moving data out of BigQuery or standing up separate ML infrastructure.

Must-know

  • You must first create a BigQuery Cloud resource connection (CREATE CONNECTION) which provisions a service account used to authenticate to Vertex AI.
  • The connection's service account needs the Vertex AI User IAM role (or equivalent permissions) granted before the remote model will work.
  • A remote model is created with CREATE MODEL ... REMOTE WITH CONNECTION, specifying the connection and the target pretrained endpoint (e.g., a Gemini model).
  • Once the remote model exists, ML.GENERATE_TEXT is used to generate text output and ML.GENERATE_EMBEDDING is used to produce vector embeddings from a table's text column, both via standard SQL.
  • The BigQuery dataset, the connection, and the Vertex AI endpoint region must be compatible (often same region) or model creation/inference will fail.
  • Calls to these remote LLM functions incur Vertex AI prediction charges in addition to normal BigQuery query costs, so usage should be monitored.
Check this objectiveFree · always available

A data analyst at a retail company wants to use a pretrained Gemini model directly from BigQuery SQL to summarize thousands of customer review rows stored in a table, without exporting any data or training a custom model. Which sequence of steps correctly enables this in BigQuery?

Your objective map0 tried · 0 right · 41 untouched

What you have tried across GCP ADP's objectives, not a readiness score.

Coverage checked against the published exam guide on Aug 12, 2026.

These are independent practice questions, written against this certification's published exam guide. They are not the certification vendor's own questions, and not the real exam.