LlamaIndex

🦙 Meet your new best friend in data wrangling! LlamaIndex is like a super-smart librarian for your LLM applications. It helps you organize, structure, and access your private or domain-specific data with style. And guess what? LlamaIndex.TS brings all that Python goodness to JavaScript land!

Supported Environments

• Node.js (Rock-solid official support) ✨
• Vercel Edge Functions (Experimental but exciting!) 🚀
• Deno (Also experimental, but living on the edge is fun!) 🦕

Quick Example: Completion

Let’s see this llama in action! Here’s how to combine the AI SDK and LlamaIndex.

// api/completion/route.ts
import { OpenAI, SimpleChatEngine } from 'llamaindex';
import { LlamaIndexAdapter } from 'ai';

export const maxDuration = 60;

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

  const llm = new OpenAI({ model: 'gpt-4o' });
  const chatEngine = new SimpleChatEngine({ llm });

  const stream = await chatEngine.chat({
    message: prompt,
    stream: true,
  });

  return LlamaIndexAdapter.toDataStreamResponse(stream);
}

For the frontend piece, you’ll want to use our completion hook.