Create a multi-turn non-streaming conversation with Vertex AI

Sample demonstrating how to set-up the Vertex AI SDK and create a non-streaming conversation with three consecutive messages sent to the model.

Code sample

Node.js

Before trying this sample, follow the Node.js setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Node.js API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

const {GoogleGenAI} = require('@google/genai');
/**
 * TODO(developer): Update these variables before running the sample.
 */
async function createNonStreamingChat(
  projectId = 'PROJECT_ID',
  location = 'us-central1',
  model = 'gemini-2.5-flash'
) {
  // Initialize client with your Cloud project and location
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const chat = client.chats.create({
    model: model,
  });

  const response1 = await chat.sendMessage({message: 'Hello'});
  console.log('Chat response 1: ', response1.text);

  const response2 = await chat.sendMessage({
    message: 'Can you tell me a scientific fun fact?',
  });
  console.log('Chat response 2: ', response2.text);

  const response3 = await chat.sendMessage({
    message: 'How can I learn more about that?',
  });
  console.log('Chat response 3: ', response3.text);
}

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.