Skip to main content

Quick Start Guide

Get started with Neuredge AI in minutes. Our platform offers state-of-the-art AI capabilities with OpenAI-compatible endpoints and multiple model options.

Installation​

JavaScript/TypeScript​

npm install @neuredge/sdk
# or
yarn add @neuredge/sdk
# or
pnpm add @neuredge/sdk

Python​

pip install neuredge-sdk
# or
poetry add neuredge-sdk

Authentication​

Sign up at Neuredge Dashboard to get your API key.

// JavaScript/TypeScript
import { Neuredge } from '@neuredge/sdk';

const neuredge = new Neuredge({
  apiKey: 'your-api-key'
});
# Python
from neuredge import Neuredge

neuredge = Neuredge(api_key='your-api-key')

OpenAI Compatibility​

Our APIs are compatible with OpenAI's SDK. Simply update the base URL:

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your-neuredge-key',
  baseURL: 'https://api.neuredge.dev/v1/'
});

Basic Examples​

1. Text Generation​

// Using OpenAI SDK
const completion = await openai.chat.completions.create({
  model: '@cf/meta/llama-3.1-8b-instruct',
  messages: [
    {role: 'user', content: 'What is artificial intelligence?'}
  ]
});

console.log(completion.choices[0].message.content);

// Using Native SDK
const response = await neuredge.generate({
  model: '@cf/meta/llama-3.1-8b-instruct',
  messages: [
    {role: 'user', content: 'What is artificial intelligence?'}
  ]
});

2. Embeddings​

// Using OpenAI SDK
const embedding = await openai.embeddings.create({
  model: '@cf/baai/bge-base-en-v1.5',
  input: 'Hello, world!'
});

// Using Native SDK
const vector = await neuredge.embeddings({
  model: '@cf/baai/bge-base-en-v1.5',
  input: 'Hello, world!'
});

3. Image Generation​

// Using Native SDK
const image = await neuredge.generateImage({
  model: '@cf/stabilityai/stable-diffusion-xl-base-1.0',
  prompt: 'A serene landscape with mountains and a lake',
  width: 1024,
  height: 1024
});

Rate Limits & Quotas​

PlanText TokensImagesEmbeddings
Free300K/month50/month300K/month
Pro ($29)3M/month500/month3M/month
Business ($49)4.5M/month750/month4.5M/month

Code Examples​

Express.js API​

import express from 'express';
import OpenAI from 'openai';

const app = express();
app.use(express.json());

const openai = new OpenAI({
  apiKey: process.env.NEUREDGE_API_KEY,
  baseURL: 'https://api.neuredge.dev/v1/'
});

app.post('/chat', async (req, res) => {
  try {
    const { messages } = req.body;
    const completion = await openai.chat.completions.create({
      model: '@cf/meta/llama-3.1-8b-instruct',
      messages
    });
    
    res.json({ 
      response: completion.choices[0].message.content 
    });
  } catch (error) {
    res.status(500).json({ error: error.message });
  }
});

Next.js API Route​

// pages/api/generate.js
import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: process.env.NEUREDGE_API_KEY,
  baseURL: 'https://api.neuredge.dev/v1/'
});

export default async function handler(req, res) {
  if (req.method !== 'POST') {
    return res.status(405).json({ message: 'Method not allowed' });
  }

  try {
    const { prompt } = req.body;
    const completion = await openai.chat.completions.create({
      model: '@cf/meta/llama-3.1-8b-instruct',
      messages: [{ role: 'user', content: prompt }]
    });

    res.status(200).json({ 
      result: completion.choices[0].message.content 
    });
  } catch (error) {
    res.status(500).json({ error: error.message });
  }
}

Best Practices​

  1. Error Handling
try {
  const response = await openai.chat.completions.create({
    model: '@cf/meta/llama-3.1-8b-instruct',
    messages: [{ role: 'user', content: prompt }]
  });
} catch (error) {
  if (error.code === 'rate_limit_exceeded') {
    // Implement backoff strategy
  } else if (error.code === 'token_limit_exceeded') {
    // Handle token limit
  } else {
    // Handle other errors
  }
}
  1. Environment Setup
// .env
NEUREDGE_API_KEY=your-api-key

// Next.js
export const runtime = 'edge' // Optional: Use edge runtime
  1. Response Streaming
const stream = await openai.chat.completions.create({
  model: '@cf/meta/llama-3.1-8b-instruct',
  messages: [{ role: 'user', content: prompt }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

Next Steps​

Explore our detailed documentation:

Or check out: