sveltekit.mdx

title
SvelteKit

You can find the project source code on GitHub. This guide provides detailed, step-by-step instructions on how to use Upstash RAG Chat with SvelteKit. You can also explore our [SvelteKit example](https://github.com/upstash/rag-chat/tree/master/examples/nextjs/sveltekit) for detailed, end-to-end examples and best practices.

Project Setup

Create a new SvelteKit application and install @upstash/rag-chat package.

npm create svelte@latest my-app
cd my-app
npm install @upstash/rag-chat

Setup Upstash Vector

Create a Vector index using Upstash Console or Upstash CLI and copy the UPSTASH_VECTOR_REST_URL and UPSTASH_VECTOR_REST_TOKEN into your .env file.

UPSTASH_VECTOR_REST_URL=<YOUR_URL>
UPSTASH_VECTOR_REST_TOKEN=<YOUR_TOKEN>

Setup QStash LLM

Navigate to QStash Console and copy the QSTASH_TOKEN into your .env file.

QSTASH_TOKEN=<YOUR_TOKEN>

Create a SvelteKit Handler

Create /src/routes/chat/+server.ts:

import { RAGChat, upstash } from "@upstash/rag-chat";
import { Index } from "@upstash/vector";
import { env } from "$env/dynamic/private";

const ragChat = new RAGChat({
  vector: new Index({
    token: env.UPSTASH_VECTOR_REST_TOKEN,
    url: env.UPSTASH_VECTOR_REST_URL
  }),
  model: upstash("meta-llama/Meta-Llama-3-8B-Instruct", {
    apiKey: env.QSTASH_TOKEN
  }),
});

export async function GET() {
  const response = await ragChat.chat("What is the speed of light?");
  return new Response(response.output, {
    headers: {
      'Content-Type': 'application/json'
    }
  });
}

Run

Run the SvelteKit application:

npm run dev

Visit http://localhost:5173/chat