Vertex AI (Enterprise)
Vertex AI JavaScript SDK Integration
Use Vertex AI’s JavaScript SDK to integrate with Helicone to log your Vertex AI usage.
Proxy Integration
Fetch
1
2
Set API keys as environment variables
export HELICONE_API_KEY=<your API key>
export GCLOUD_API_KEY=<your Google Cloud API key>
3
Install necessary packages
Ensure you have the necessary packages installed in your Javascript project:
npm install node-fetch
4
Send a request using fetch
const fetch = require('node-fetch');
const url = 'https://gateway.helicone.ai/v1/projects/your-project-id/locations/your-location/publishers/google/models/model-name:streamGenerateContent';
const headers = {
'Authorization': `Bearer ${process.env.GCLOUD_API_KEY}`,
'Content-Type': 'application/json',
'Helicone-Auth': `Bearer ${process.env.HELICONE_API_KEY}`,
'Helicone-Target-URL': `https://${LOCATION}-aiplatform.googleapis.com`,
'User-Agent': 'node-fetch'
};
const body = JSON.stringify({
contents: {
role: 'user',
parts: { text: 'Which theaters in Mountain View show Barbie movie?' }
},
generation_config: { maxOutputTokens: 1 }
});
fetch(url, { method: 'POST', headers: headers, body: body })
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
VertexAI SDK
1
2
Set API keys as environment variables
export HELICONE_API_KEY=<your API key>
export GCLOUD_API_KEY=<your Google Cloud API key>
3
Install necessary packages
Ensure you have the necessary packages installed in your Javascript project:
npm install @google-cloud/vertexai
4
Import VertexAI and configure the client
import { VertexAI } from "@google-cloud/vertexai";
const vertex_ai = new VertexAI({
project: "your-project-id",
location: "your-location",
apiEndpoint: "gateway.helicone.ai",
});
5
Set up custom headers
const customHeaders = new Headers({
"Helicone-Auth": `Bearer ${process.env.HELICONE_API_KEY}`,
"Helicone-Target-URL": `https://${LOCATION}-aiplatform.googleapis.com`,
});
6
Define request options
const requestOptions = {
customHeaders: customHeaders,
} as RequestOptions;
7
Get the generative model
const generativeModel = vertex_ai.preview.getGenerativeModel(
{
model: "model-name"
},
requestOptions // Pass request options
);
8
Generate content
const result = await generativeModel.generateContent({
contents: [{ role: "user", parts: [{ text: "How are you doing today?" }] }],
});
console.log(result);