Build Real-Time AI/ML APIs Using Only SQL (BigQuery/Vertex on GCP)
Learn how to build advanced AI models using only SQL and deploy them as production-grade real-time APIs with BigQuery ML (BQML) and Vertex AI. This tutorial walks through creating a BQML logistic regression model to predict financial defaults, exporting the trained model, and serving it as an API endpoint on Vertex AI. See how to enable logging, monitoring, and drift detection for an MLOps-ready solution.
Demonstration Code and Diagram: https://github.com/nodematiclabs/ml-a...
Free Trial - Our New Diagram Tool: https://softwaresim.com/pricing/ ("YOUTUBE24" for 25% Off)
If you are a cloud, DevOps, or software engineer you’ll probably find our wide range of YouTube tutorials, demonstrations, and walkthroughs useful - please consider subscribing to support the channel.
0:00 Conceptual Overview
1:52 BigQuery Dataset
2:37 BQML SQL (Model Creation)
4:17 BQML Model Details
5:29 Model Export (GCS)
7:02 Model Import (Vertex AI)
7:49 Vertex AI Endpoints API
9:02 Model Testing via API