QuickEmbed AI Node.js SDK 🚀

The official Node.js SDK for the QuickEmbed AI Platform (quickembedai.com).

Add RAG-powered AI chatbots to your software in just 5 lines of code.

QuickEmbed AI is an enterprise-grade RAG-as-a-Service platform. It eliminates the complexity of vector databases, chunking strategies, and LLM orchestration, allowing you to focus on your product.

🔗 Links

• Official Website: quickembedai.com
• Full Documentation: https://quickembedai.com/help-center
• API Dashboard: quickembedai.com/dashboard/developers

💻 Installation

npm install @quickembedai/sdk

⚡ Quick Start (5 Lines of Code)

import { QuickEmbedAIClient } from '@quickembedai/sdk';

const client = new QuickEmbedAIClient('YOUR_API_KEY');

// 1. Ingest Data (URL, File, or Text)
await client.ingestUrl('https://docs.yourcompany.com', 'your-tenant-id');

// 2. Query with RAG (Instant Answer)
const { answer } = await client.query('How does the product work?', 'your-tenant-id');

console.log(answer);

🎯 Key Features

• TypeScript First: Full type safety for Enterprise applications.
• Universal SDK: Works perfectly in Node.js backends, Edge functions, and Browser environments.
• Multi-Tenant Architecture: Isolate data effortlessly using tenant_id.
• Streaming Support: Real-time token streaming for a ChatGPT-like experience.
• Insights & Analytics: Access document health scores and AI-generated insights via the SDK.

📖 API Reference

new QuickEmbedAIClient(apiKey, options)

• apiKey: Your secret API key from the developer dashboard.
• options.baseUrl: Defaults to https://quickembedai.com/api/v1.

client.query(message, tenantId, options)

Standard RAG inquiry. Returns { answer, sources }.

client.queryStream(message, tenantId, onChunk, options)

Streams AI responses token-by-token. Ideal for real-time UIs.

client.ingestUrl(url, tenantId)

Crawl and index content from any public URL.

client.ingestFile(filePath, tenantId)

Process and vectorize local PDF, DOCX, or CSV files.

🛡️ License

MIT © QuickEmbed AI Team