Build with Vercel - SambaNova Integration Guide

Vercel is a platform for deploying and hosting web applications, which developers can use to easily manage their websites and serverless functions.

Prerequisites

A SambaCloud account
A SambaNova API key
Node.js 18 or later

Setup

The SambaNova provider is available via the sambanova-ai-provider module. You can install it with:

npm install sambanova-ai-provider

yarn add sambanova-ai-provider

pnpm add sambanova-ai-provider

Environment variables

Create a .env file in your project root:

SAMBANOVA_API_KEY=your-sambacloud-api-key

Provider instance

You can import the default provider instance sambanova from sambanova-ai-provider:

import { sambanova } from 'sambanova-ai-provider';

If you need a customized setup, you can import createSambaNova from sambanova-ai-provider and create a provider instance with your settings:

import { createSambaNova } from 'sambanova-ai-provider';

const sambanova = createSambaNova({
  // Optional settings
});

You can use the following optional settings to customize the SambaNova provider instance:

baseURL string Use a different URL prefix for API calls, e.g. to use proxy servers. The default prefix is https://api.sambanova.ai/v1.
apiKey string API key that is being sent using the Authorization header. It defaults to the SAMBANOVA_API_KEY environment variable.
headers Record<string,string> Custom headers to include in the requests.
fetch (input: RequestInfo, init?: RequestInit) => Promise<Response> Custom fetch implementation. Defaults to the global fetch function. You can use it as a middleware to intercept requests, or to provide a custom fetch implementation for e.g. testing.

Models

You can use any of the SambaCloud models on a provider instance. The first argument is the model id, e.g. Meta-Llama-3.3-70B-Instruct.

const model = sambanova('Meta-Llama-3.3-70B-Instruct');

Example usage

Basic demonstration of text generation using the SambaNova provider.

import { createSambaNova } from 'sambanova-ai-provider';
import { generateText } from 'ai';

const sambanova = createSambaNova({
  apiKey: 'YOUR_API_KEY',
});

const model = sambanova('Meta-Llama-3.3-70B-Instruct');

const { text } = await generateText({
  model,
  prompt: 'Hello, nice to meet you.',
});

console.log(text);

You’ll receive an output similar to the following:

Hello. Nice to meet you too. Is there something I can help you with or would you like to chat?

Intercepting fetch requests

Intercepting fetch requests is supported. See the Vercel AI SDK example for intercepting fetch requests.

Example

import { createSambaNova } from 'sambanova-ai-provider';
import { generateText } from 'ai';

const sambanovaProvider = createSambaNova({
  apiKey: 'YOUR_API_KEY',
  fetch: async (url, options) => {
    console.log('URL', url);
    console.log('Headers', JSON.stringify(options.headers, null, 2));
    console.log(`Body ${JSON.stringify(JSON.parse(options.body), null, 2)}`);
    return await fetch(url, options);
  },
});

const model = sambanovaProvider('Meta-Llama-3.3-70B-Instruct');

const { text } = await generateText({
  model,
  prompt: 'Hello, nice to meet you.',
});

Example output

URL https://api.sambanova.ai/v1/chat/completions
Headers {
  "Content-Type": "application/json",
  "Authorization": "Bearer YOUR_API_KEY"
}
Body {
  "model": "Meta-Llama-3.3-70B-Instruct",
  "temperature": 0,
  "messages": [
    {
      "role": "user",
      "content": "Hello, nice to meet you."
    }
  ]
}

Troubleshooting

Authentication error or 401 Unauthorized

Verify SAMBANOVA_API_KEY is set in your .env file and matches the key from the SambaNova API dashboard.

Module not found: sambanova-ai-provider

Run npm install sambanova-ai-provider (or yarn add / pnpm add). Verify your package manager matches the install command.

Model not found or invalid model ID

Check the model ID is correct. See available models for valid IDs.

Overview

Developer tools

Frameworks

Interfaces and low-code

Data and infrastructure

Multimodal

Evaluation and monitoring

Vercel integration guide

Prerequisites

Setup

Environment variables

Provider instance

Models

Example usage

Intercepting fetch requests

Example

Example output

Troubleshooting

​Prerequisites

​Setup

​Environment variables

​Provider instance

​Models

​Example usage

​Intercepting fetch requests

​Example

​Example output

​Troubleshooting

Prerequisites

Setup

Environment variables

Provider instance

Models

Example usage

Intercepting fetch requests

Example

Example output

Troubleshooting