Integrating AI into Web Apps: Architecture, Streaming & Production Best Practices

import { NextRequest, NextResponse } from 'next/server';
import { Redis } from '@upstash/redis';
import { Ratelimit } from '@upstash/ratelimit';

// Initialize Redis Rate Limiting (10 AI requests per minute per IP)
const redis = new Redis({
  url: process.env.UPSTASH_REDIS_REST_URL!,
  token: process.env.UPSTASH_REDIS_REST_TOKEN!,
});

const ratelimit = new Ratelimit({
  redis,
  limiter: Ratelimit.slidingWindow(10, '60 s'),
});

export const runtime = 'edge';

export async function POST(req: NextRequest) {
  const ip = req.headers.get('x-forwarded-for') || '127.0.0.1';
  const { success } = await ratelimit.limit(ip);

  if (!success) {
    return NextResponse.json(
      { error: 'Rate limit exceeded. Please wait a minute before sending more queries.' },
      { status: 429 }
    );
  }

  const { prompt } = await req.json();
  if (!prompt || typeof prompt !== 'string' || prompt.length > 2000) {
    return NextResponse.json({ error: 'Invalid prompt payload.' }, { status: 400 });
  }

  // Forward to LLM Provider via Edge Fetch
  const response = await fetch('https://api.openai.com/v1/chat/completions', {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      model: 'gpt-4o',
      messages: [
        {
          role: 'system',
          content: 'You are a concise, enterprise technical assistant at Rajput Bhavin Engineering.',
        },
        { role: 'user', content: prompt },
      ],
      stream: true,
      max_tokens: 1000,
    }),
  });

  if (!response.ok) {
    return NextResponse.json({ error: 'Upstream AI provider error' }, { status: 502 });
  }

  return new Response(response.body, {
    headers: {
      'Content-Type': 'text/event-stream; charset=utf-8',
      'Cache-Control': 'no-cache, no-transform',
    },
  });
}