You to use Gemini LLM and other models on Google Cloud Platform via VertexAI. Read more about all the supported LLMs. To get started, you need to set the right access credentials to google cloud. You have two options here -
  • Authenticate by using gcloud CLI:
gcloud auth application-default login
  • Authentication using Service Account with JSON key and environment variable:
GOOGLE_APPLICATION_CREDENTIALS="<Path to credentials.json>"
Once this is done, you can configure your embedJs app -

​
Install VertexAi addon

npm install @llm-tools/embedjs-vertexai

​
Usage

import { RAGApplicationBuilder } from '@llm-tools/embedjs';
import { Ollama } from '@llm-tools/embedjs-vertexai';

const app = await new RAGApplicationBuilder()
.setModel(new VertexAI({ modelName: 'gemini-1.5-pro-preview-0409'}))