Deployment & Scaling · Advanced
BigQuery ML: AI Where the Data Already Lives
Train classical models and call Gemini from SQL, without moving a byte out of the warehouse — plus the slot-cost arithmetic that decides whether that is clever or catastrophic.
- 1.3 hours lesson
- intermediate level
- Google Cloud AI Track
- Narrated presentation
What you’ll learn
- CREATE MODEL / ML.PREDICT for classical models entirely in SQL
- Remote models connecting BigQuery to Gemini
- ML.GENERATE_TEXT, AI.GENERATE, AI.GENERATE_TABLE and ML.GENERATE_EMBEDDING
- BigQuery vector search with VECTOR_SEARCH and vector indexes
- Per-row generative cost multiplied by row count — computed before the full run
- Deduplicate and filter-to-changed as the two main cost controls
- Batch analytics fit; not a low-latency online serving path
Inside this lesson
A narrated, slide-by-slide presentation with 1 prediction exercise, 1 knowledge check, 4 videos. You answer as you go, and the platform checks your work.