@arelis-ai/governance-providers-google-vertex

Google Vertex AI (Gemini / Model Garden) provider adapter for Arelis.

Install

pnpm add @arelis-ai/governance-providers-google-vertex

Usage

import {
  createArelisClient,
  createModelRegistry,
  createAllowAllEngine,
  createConsoleSink,
} from '@arelis-ai/arelis-governance-sdk';
import { VertexAIProvider } from '@arelis-ai/governance-providers-google-vertex';

const provider = new VertexAIProvider(
  {
    projectId: 'my-project',
    location: 'us-central1',
    auth: { accessToken: process.env.GOOGLE_ACCESS_TOKEN! },
  },
  ['gemini-1.5-flash', 'gemini-1.5-pro']
);

const registry = createModelRegistry();
registry.register(provider);

const client = createArelisClient({
  modelRegistry: registry,
  policyEngine: createAllowAllEngine(),
  auditSink: createConsoleSink(),
});

const result = await client.models.generate({
  model: 'gemini-1.5-flash',
  request: {
    model: 'gemini-1.5-flash',
    messages: [{ role: 'user', content: 'Hello Vertex' }],
  },
  context: {
    org: { id: 'org_1' },
    actor: { type: 'human', id: 'user_1' },
    purpose: 'testing',
    environment: 'dev',
  },
});

console.log(result.output.content);

Auth

Provide either:

• auth: { accessToken: string }
• auth: { getAccessToken: () => Promise<string> }

Notes

• Uses Vertex REST endpoints with generateContent and streamGenerateContent.
• Tool calling and multimodal inputs are mapped to Vertex function declarations and inline image data.