Back to AI/ML

Vertex AI

gcp

Unified enterprise AI platform for training, tuning, and deploying generative AI and custom ML models.

AI & ML
Google Cloud Platform

Unified enterprise AI platform for training, tuning, and deploying generative AI and custom ML models.

Click any section above to jump directly to it

What is Vertex AI?

Google Cloud Vertex AI is a unified machine learning platform that brings all of Google's AI tools, foundation models (Gemini 1.5 Pro/Flash, Imagen, Codey), and MLOps infrastructure into a single integrated console and API. From prompt engineering in Vertex AI Studio to custom distributed neural network training on NVIDIA H100 GPUs and Cloud TPUs, Vertex AI provides enterprise governance, vector embeddings search, and real-time model serving.

Decision Guide: When to Choose This Service

When to Use Vertex AI

Use Vertex AI for enterprise GenAI applications (Gemini models, Model Garden, vector search embeddings), training custom TensorFlow/PyTorch/scikit-learn models on GPUs/TPUs, feature stores, and production model serving with autoscaling endpoints.

When NOT to Use (Recommended Alternatives)

Do NOT use Vertex AI if you only need simple SQL-based tabular predictions on BigQuery data (use BigQuery ML instead without leaving SQL).

Core Architectural Pillars

Vertex AI Studio & Model Garden

Interactive playground for prompting and fine-tuning foundation models (Gemini 1.5, Anthropic Claude, Llama 3, Mistral).

Model Registry & Endpoints

Model Registry versions trained model artifacts; Endpoints provide autoscaling HTTPS REST/gRPC prediction endpoints.

Vector Search (Matching Engine)

Petabyte-scale vector database for semantic search and Retrieval Augmented Generation (RAG).

Feature Store

Centralized repository to serve, share, and prevent training-serving skew in ML feature values.

Grounding with Google Search & Enterprise Data

Anchor GenAI responses in real-time factual data from Google Search or private BigQuery/GCS repositories.