Class AntsVertexAI

java.lang.Object

com.ants.platform.guardrails.providers.AntsVertexAI

public class AntsVertexAI
extends Object

Google Vertex AI (Gemini) wrapper with guardrail enforcement and trace logging.

Uses the Vertex AI REST API with Application Default Credentials (ADC). The access token is obtained via gcloud auth print-access-token or can be provided directly via the builder.

 var client = AntsVertexAI.builder()
     .projectId("my-gcp-project")
     .location("us-central1")
     .antsApiKey("pk:sk")
     .agentId("agent_123")
     .build();

 JsonNode response = client.generateContent(
     "gemini-2.0-flash",
     List.of(Map.of("role", "user", "content", "Hello"))
 );
 

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	AntsVertexAI.Builder

Method Summary

Modifier and Type	Method	Description
static AntsVertexAI.Builder	builder()
com.fasterxml.jackson.databind.JsonNode	generateContent(String model, List<Map<String,String>> messages)	Generate content using Vertex AI with guardrail checks.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Details

builder

public static AntsVertexAI.Builder builder()

generateContent

public com.fasterxml.jackson.databind.JsonNode generateContent(String model,
 List<Map<String,String>> messages)

Generate content using Vertex AI with guardrail checks. A trace is logged asynchronously after each call.

Parameters:

model - Gemini model ID (e.g. "gemini-2.0-flash")

messages - list of message maps with "role" and "content" keys

Returns:

raw JSON response from the Vertex AI generateContent API