JavaScript SDK

The official OpenAI JavaScript/TypeScript SDK works seamlessly with Assisters API in both Node.js and browser environments.

Installation

npm install openai

Quick Start

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'ask_your_api_key',
  baseURL: 'https://api.assisters.dev/v1'
});

const response = await client.chat.completions.create({
  model: 'llama-3.1-8b',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello!' }
  ]
});

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

Configuration

Environment Variables

export ASSISTERS_API_KEY="ask_your_api_key"

const client = new OpenAI({
  apiKey: process.env.ASSISTERS_API_KEY,
  baseURL: 'https://api.assisters.dev/v1'
});

Client Options

const client = new OpenAI({
  apiKey: 'ask_...',
  baseURL: 'https://api.assisters.dev/v1',
  timeout: 30000,        // Request timeout in ms
  maxRetries: 3,         // Automatic retries
  defaultHeaders: {...}, // Custom headers
});

Chat Completions

Basic Request

const response = await client.chat.completions.create({
  model: 'llama-3.1-8b',
  messages: [
    { role: 'user', content: 'What is machine learning?' }
  ],
  temperature: 0.7,
  max_tokens: 500
});

console.log(response.choices[0].message.content);
console.log(`Tokens used: ${response.usage.total_tokens}`);

Streaming

const stream = await client.chat.completions.create({
  model: 'llama-3.1-8b',
  messages: [{ role: 'user', content: 'Write a poem about JavaScript' }],
  stream: true
});

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

Multi-turn Conversation

const messages = [
  { role: 'system', content: 'You are a math tutor.' }
];

async function chat(userMessage) {
  messages.push({ role: 'user', content: userMessage });

  const response = await client.chat.completions.create({
    model: 'llama-3.1-8b',
    messages
  });

  const assistantMessage = response.choices[0].message.content;
  messages.push({ role: 'assistant', content: assistantMessage });

  return assistantMessage;
}

console.log(await chat('What is 2 + 2?'));
console.log(await chat('And if I multiply that by 3?'));

Embeddings

const response = await client.embeddings.create({
  model: 'e5-large-v2',
  input: 'The quick brown fox jumps over the lazy dog'
});

const embedding = response.data[0].embedding;
console.log(`Dimensions: ${embedding.length}`); // 1024

// Batch embeddings
const batchResponse = await client.embeddings.create({
  model: 'e5-large-v2',
  input: ['First text', 'Second text', 'Third text']
});

batchResponse.data.forEach((data, i) => {
  console.log(`Text ${i}: ${data.embedding.length} dimensions`);
});

Moderation

const response = await client.moderations.create({
  model: 'llama-guard-3',
  input: 'Hello, how are you today?'
});

const result = response.results[0];
console.log(`Flagged: ${result.flagged}`);
console.log(`Categories:`, result.categories);
console.log(`Scores:`, result.category_scores);

TypeScript Support

Full TypeScript support with type definitions:

import OpenAI from 'openai';
import type {
  ChatCompletion,
  ChatCompletionMessageParam
} from 'openai/resources/chat/completions';

const client = new OpenAI({
  apiKey: process.env.ASSISTERS_API_KEY!,
  baseURL: 'https://api.assisters.dev/v1'
});

async function getResponse(prompt: string): Promise<string> {
  const messages: ChatCompletionMessageParam[] = [
    { role: 'user', content: prompt }
  ];

  const response: ChatCompletion = await client.chat.completions.create({
    model: 'llama-3.1-8b',
    messages
  });

  return response.choices[0].message.content ?? '';
}

Error Handling

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'ask_...',
  baseURL: 'https://api.assisters.dev/v1'
});

try {
  const response = await client.chat.completions.create({
    model: 'llama-3.1-8b',
    messages: [{ role: 'user', content: 'Hello' }]
  });
} catch (error) {
  if (error instanceof OpenAI.AuthenticationError) {
    console.log('Invalid API key');
  } else if (error instanceof OpenAI.RateLimitError) {
    console.log('Rate limited. Retry after:', error.headers?.['retry-after']);
  } else if (error instanceof OpenAI.BadRequestError) {
    console.log('Bad request:', error.message);
  } else if (error instanceof OpenAI.APIError) {
    console.log('API error:', error.status, error.message);
  }
}

Browser Usage

The SDK works in browsers, but never expose your API key client-side. Use a backend proxy:

Backend Proxy (Recommended)

// Server-side (Next.js API route)
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.ASSISTERS_API_KEY,
  baseURL: 'https://api.assisters.dev/v1'
});

export async function POST(req) {
  const { message } = await req.json();

  const response = await client.chat.completions.create({
    model: 'llama-3.1-8b',
    messages: [{ role: 'user', content: message }]
  });

  return Response.json({
    content: response.choices[0].message.content
  });
}

// Client-side
async function sendMessage(message) {
  const res = await fetch('/api/chat', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({ message })
  });

  const data = await res.json();
  return data.content;
}

Framework Integration

Next.js

// app/api/chat/route.ts
import OpenAI from 'openai';
import { NextResponse } from 'next/server';

const client = new OpenAI({
  apiKey: process.env.ASSISTERS_API_KEY!,
  baseURL: 'https://api.assisters.dev/v1'
});

export async function POST(req: Request) {
  const { messages } = await req.json();

  const response = await client.chat.completions.create({
    model: 'llama-3.1-8b',
    messages
  });

  return NextResponse.json(response);
}

Express

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

const app = express();
const client = new OpenAI({
  apiKey: process.env.ASSISTERS_API_KEY,
  baseURL: 'https://api.assisters.dev/v1'
});

app.use(express.json());

app.post('/chat', async (req, res) => {
  const { message } = req.body;

  const response = await client.chat.completions.create({
    model: 'llama-3.1-8b',
    messages: [{ role: 'user', content: message }]
  });

  res.json({ content: response.choices[0].message.content });
});

app.listen(3000);

Vercel AI SDK

import { createOpenAI } from '@ai-sdk/openai';
import { generateText, streamText } from 'ai';

const assisters = createOpenAI({
  apiKey: process.env.ASSISTERS_API_KEY,
  baseURL: 'https://api.assisters.dev/v1'
});

// Non-streaming
const { text } = await generateText({
  model: assisters('llama-3.1-8b'),
  prompt: 'Hello!'
});

// Streaming
const result = await streamText({
  model: assisters('llama-3.1-8b'),
  prompt: 'Write a poem'
});

for await (const textPart of result.textStream) {
  process.stdout.write(textPart);
}

React Hook Example

import { useState, useCallback } from 'react';

interface Message {
  role: 'user' | 'assistant';
  content: string;
}

export function useChat() {
  const [messages, setMessages] = useState<Message[]>([]);
  const [isLoading, setIsLoading] = useState(false);

  const sendMessage = useCallback(async (content: string) => {
    const userMessage: Message = { role: 'user', content };
    setMessages(prev => [...prev, userMessage]);
    setIsLoading(true);

    try {
      const res = await fetch('/api/chat', {
        method: 'POST',
        headers: { 'Content-Type': 'application/json' },
        body: JSON.stringify({
          messages: [...messages, userMessage]
        })
      });

      const data = await res.json();
      const assistantMessage: Message = {
        role: 'assistant',
        content: data.choices[0].message.content
      };

      setMessages(prev => [...prev, assistantMessage]);
    } finally {
      setIsLoading(false);
    }
  }, [messages]);

  return { messages, sendMessage, isLoading };
}

Best Practices

Use Environment Variables

Never expose API keys in client-side code

Use Backend Proxy

Always route browser requests through your server

Enable Streaming

Use streaming for better chat UX

Handle Errors

Catch and handle API errors gracefully

Getting Started

Guides

SDKs

Billing

Security

JavaScript SDK

JavaScript SDK

Installation

Quick Start

Configuration

Environment Variables

Client Options

Chat Completions

Basic Request

Streaming

Multi-turn Conversation

Embeddings

Moderation

TypeScript Support

Error Handling

Browser Usage

Backend Proxy (Recommended)

Framework Integration

Next.js

Express

Vercel AI SDK

React Hook Example

Best Practices

Use Environment Variables

Use Backend Proxy

Enable Streaming

Handle Errors

Getting Started

Guides

SDKs

Billing

Security

​JavaScript SDK

​Installation

​Quick Start

​Configuration

​Environment Variables

​Client Options

​Chat Completions

​Basic Request

​Streaming

​Multi-turn Conversation

​Embeddings

​Moderation

​TypeScript Support

​Error Handling

​Browser Usage

​Backend Proxy (Recommended)

​Framework Integration

​Next.js

​Express

​Vercel AI SDK

​React Hook Example

​Best Practices

Use Environment Variables

Use Backend Proxy

Enable Streaming

Handle Errors

JavaScript SDK

Installation

Quick Start

Configuration

Environment Variables

Client Options

Chat Completions

Basic Request

Streaming

Multi-turn Conversation

Embeddings

Moderation

TypeScript Support

Error Handling

Browser Usage

Backend Proxy (Recommended)

Framework Integration

Next.js

Express

Vercel AI SDK

React Hook Example

Best Practices