How to Use Vultr Serverless Inference in Node.js

Vultr Serverless Inference allows you to run inference workloads for large language models such as Mixtral 8x7B, Mistral 7B, Meta Llama 2 70B, and more. Using Vultr Serverless Inference, you can run inference workloads without having to worry about the infrastructure, and you only pay for the input and output tokens.

This guide demonstrates step-by-step process to start using Vultr Serverless Inference in Node.js.

Prerequisites

Before you begin, you must:

• Create a Vultr Serverless Inference Subscription
• Fetch the API key for Vultr Serverless Inference
• Node.js 20.x or later

Set Up the Environment

1. Create a new project directory and navigate to the project directory.

   CONSOLE

   Copy

   $ mkdir vultr-serverless-inference-nodejs
   $ cd vultr-serverless-inference-nodejs

   Explain Code

   Powered by Vultr AgentBeta

2. Create a new Node.js project.

   CONSOLE

   Copy

   $ npm init -y

   Explain Code

   Powered by Vultr AgentBeta

3. Install the required Node.js packages.

   CONSOLE

   Copy

   $ npm install openai

   Explain Code

   Powered by Vultr AgentBeta

   Note

   Please note that you only need to install the openai package if you are using the OpenAI SDK for Vultr Serverless Inference.

Inference via Direct API Calls

Vultr Serverless Inference provides a RESTful API to run inference workloads. You can use the fetch built-in module to make the API calls.

1. Create a new JavaScript file name inference.js.

   CONSOLE

   Copy

   $ nano inference.js

   Explain Code

   Powered by Vultr AgentBeta

2. Add the following code to inference.js.

   JAVASCRIPT

   Copy

   const apiKey = process.env.VULTR_SERVERLESS_INFERENCE_API_KEY;
   
   // Set the model
   // List of available models: https://api.vultrinference.com/v1/chat/models
   const model = '';
   const messages = [
       {
           "role": "user",
           "content": "What is the capital of India?"
       }
   ]
   
   const headers = {
       'Authorization': `Bearer ${apiKey}`,
       'Content-Type': 'application/json'
   }
   
   const url = 'https://api.vultrinference.com/v1/chat/completions';
   const options = {
   method: 'POST',
   headers,
   body: JSON.stringify({model, messages})
   };
   
   fetch(url, options)
       .then(output => output.json())
       .then(output => {
           const llmResponse = output.choices[0].message.content;
           console.log(llmResponse);
       })

   Explain Code

   Powered by Vultr AgentBeta

3. Run the JavaScript script.

   CONSOLE

   Copy

   $ export VULTR_SERVERLESS_INFERENCE_API_KEY=<your_api_key>
   $ node inference.js

   Explain Code

   Powered by Vultr AgentBeta

   Here, we are making a POST request to https://api.vultrinference.com/v1/chat/completions with the required headers and data. The messages list contains the list of messages for which we want to generate completions, role can be either system, user or assistant, and content is the message content.

   To maintain conversation context, you can add the previous messages to the messages list. You can also use the stream parameter to get real-time completions. For more information, refer to the Vultr Serverless Inference API documentation.

Inferencing via OpenAI SDK

If you are using the OpenAI SDK for Vultr Serverless Inference, you can use the openai package to make the API calls.

1. Create a new JavaScript file name inference_openai.js.

   CONSOLE

   Copy

   $ nano inference_openai.js

   Explain Code

   Powered by Vultr AgentBeta

2. Add the following code to inference_openai.js.

   JAVASCRIPT

   Copy

   const { OpenAI } = require("openai");
   
   const apiKey = process.env.VULTR_SERVERLESS_INFERENCE_API_KEY
   const client = new OpenAI({
       apiKey,
       baseURL: "https://api.vultrinference.com/v1"
   });
   
   // Set the model
   // List of available models: https://api.vultrinference.com/v1/chat/models
   const model = '';
   const messages = [
       {
           "role": "user",
           "content": "What is the capital of India?"
       }
   ]
   
   async function main() {
       const output = await client.chat.completions.create({ messages, model});
       const llmResponse = output.choices[0].message.content;
   
       console.log(llmResponse);
   }
   
   main();

   Explain Code

   Powered by Vultr AgentBeta

3. Run the JavaScript script.

   CONSOLE

   Copy

   $ export VULTR_SERVERLESS_INFERENCE_API_KEY=<your_api_key>
   $ node inference_openai.js

   Explain Code

   Powered by Vultr AgentBeta

   Here, we are using the openai package to make the API calls. The messages list contains the list of messages for which we want to generate completions, role can be either system, user or assistant, and content is the message content.

Conclusion

In this guide, you learned how to use Vultr Serverless Inference in Node.js. You also learned how to make direct API calls and use the OpenAI SDK for Vultr Serverless Inference. You can now integrate Vultr Serverless Inference into your Node.js applications to generate completions for large language models.