Google Cloud Services - Vertex AI

This extension allows to inject a com.google.cloud.vertexai.VertexAI object inside your Quarkus application.

Be sure to have read the Google Cloud Services extension pack global documentation before this one, it contains general configuration and information.

Bootstrapping the project

First, we need a new project.Create a new project with the following command (replace the version placeholder with the correct one):

mvn io.quarkus:quarkus-maven-plugin:<quarkusVersion>:create \
    -DprojectGroupId=org.acme \
    -DprojectArtifactId=spanner-quickstart \
    -Dextensions="resteasy-reactive-jackson,quarkus-google-cloud-vertex-ai"
cd spanner-quickstart

This command generates a Maven project, importing the Google Cloud Spanner extension.

If you already have your Quarkus project configured, you can add the quarkus-google-cloud-vertex-ai extension to your project by running the following command in your project base directory:

./mvnw quarkus:add-extension -Dextensions="quarkus-google-cloud-vertex-ai"

This will add the following to your pom.xml:

<dependency>
    <groupId>io.quarkiverse.googlecloudservices</groupId>
    <artifactId>quarkus-google-cloud-vertex-ai</artifactId>
</dependency>

Some example

This is an example usage of the extension: we create a REST resource with a single endpoint that takes a prompt as query parameter a do a prediction using a Generative Model configured with Gemini Flash.

import java.io.IOException;

import jakarta.inject.Inject;
import jakarta.ws.rs.GET;
import jakarta.ws.rs.Path;
import jakarta.ws.rs.QueryParam;

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.generativeai.GenerativeModel;

@Path("/vertexai")
public class VertexAIResource {
    @Inject
    VertexAI vertexAI;

    @GET
    public String predict(@QueryParam("prompt") String prompt) throws IOException {
        var model = new GenerativeModel("gemini-2.0-flash-001", vertexAI);
        var response = model.generateContent(prompt);

        return response.toString();
    }
}

Configuration Reference

Configuration property fixed at build time - All other configuration properties are overridable at runtime

Configuration property

Type

Default

quarkus.google.cloud.vertexai.location

Google Cloud region.

Environment variable: QUARKUS_GOOGLE_CLOUD_VERTEXAI_LOCATION

string

quarkus.google.cloud.vertexai.api-endpoint

Vertex AI API endpoint.

Environment variable: QUARKUS_GOOGLE_CLOUD_VERTEXAI_API_ENDPOINT

string