Skip to content

Getting Started with GCP Vertex AI Gemini

This guide shows how to set up a minimal deployment to use the TensorZero Gateway with GCP Vertex AI Gemini.

Setup

For this minimal setup, you’ll need just two files in your project directory:

  • Directoryconfig/
    • tensorzero.toml
  • docker-compose.yml

For production deployments, see our Deployment Guide.

Configuration

Create a minimal configuration file that defines a model and a simple chat function:

config/tensorzero.toml
[models.gemini_1_5_flash_001]
routing = ["gcp_vertex_gemini"]
[models.gemini_1_5_flash_001.providers.gcp_vertex_gemini]
type = "gcp_vertex_gemini"
model_id = "gemini-1.5-flash-001"
location = "us-central1"
project_id = "your-project-id" # change this
[functions.my_function_name]
type = "chat"
[functions.my_function_name.variants.my_variant_name]
type = "chat_completion"
model = "gemini_1_5_flash_001"
# Disable observability to keep this example minimal (not recommended in production)
[gateway]
disable_observability = true

See the list of models available on GCP Vertex AI Gemini.

Credentials

You must generate a GCP service account key in JWT form (described here) and point to it in the GCP_VERTEX_CREDENTIALS_PATH environment variable.

Deployment (Docker Compose)

Create a minimal Docker Compose configuration:

docker-compose.yml
# This is a simplified example for learning purposes. Do not use this in production.
# For production-ready deployments, see: https://www.tensorzero.com/docs/gateway/deployment
services:
gateway:
image: tensorzero/gateway
volumes:
- ./config:/app/config:ro
- ${GCP_VERTEX_CREDENTIALS_PATH:-/dev/null}:/app/gcp-credentials.json:ro
environment:
- GCP_VERTEX_CREDENTIALS_PATH=${GCP_VERTEX_CREDENTIALS_PATH:+/app/gcp-credentials.json}
ports:
- "3000:3000"

You can start the gateway with docker compose up.

Inference

Make an inference request to the gateway:

Terminal window
curl -X POST http://localhost:3000/inference \
-H "Content-Type: application/json" \
-d '{
"function_name": "my_function_name",
"input": {
"messages": [
{
"role": "user",
"content": "What is the capital of Japan?"
}
]
}
}'