AI Gateway AI Gateway AI Gateway

Bước 1: Tạo AI Gateway Step 1: Create the AI Gateway ជំហាន 1: បង្កើត AI Gateway

Chúng ta đang xây What we're building អ្វីដែលយើងកំពុងសង់

An AI Gateway configured in the Cloudflare Dashboard.

Vì sao quan trọng Why this matters ហេតុអ្វីសំខាន់

The gateway sits between your Worker and the AI models, providing observability and caching without changing your application logic.

1. Go to the Cloudflare Dashboard
2. Select AI > AI Gateway
3. Click Create Gateway
4. Name it bookmark-gateway and click Create

Bước 2: Sửa lời gọi AI Step 2: Update the AI Calls ជំហាន 2: កែការហៅ AI

Chúng ta đang xây What we're building អ្វីដែលយើងកំពុងសង់

All env.AI.run() calls routed through AI Gateway.

Vì sao quan trọng Why this matters ហេតុអ្វីសំខាន់

Adding the gateway option enables caching, monitoring, and rate limiting for every AI request.

Cập nhật generateSummary Update generateSummary ធ្វើបច្ចុប្បន្នភាព generateSummary

// CHANGED: added gateway option as third argument
async function generateSummary(title: string, url: string, env: Env): Promise<string> {
  try {
    const response = await env.AI.run('@cf/meta/llama-3.1-8b-instruct-fast', {
      messages: [
        {
          role: 'system',
          content: 'You are a helpful assistant that writes concise bookmark descriptions. Respond with exactly one sentence, no more than 20 words.'
        },
        {
          role: 'user',
          content: `Write a one-sentence description for this bookmark:\nTitle: ${title}\nURL: ${url}`
        }
      ]
    }, {
      gateway: {
        id: 'bookmark-gateway',
        skipCache: false,
        cacheTtl: 86400  // Cache summaries for 24 hours
      }
    });

    return response.response?.trim() || '';
  } catch (error) {
    console.error('AI summary failed:', error);
    return '';
  }
}

Bước 3: Test cache Gateway Step 3: Test Gateway Caching ជំហាន 3: Test cache Gateway

Chúng ta đang xây What we're building អ្វីដែលយើងកំពុងសង់

Verified that duplicate AI requests are served from the gateway cache.

Vì sao quan trọng Why this matters ហេតុអ្វីសំខាន់

Cache hits mean faster responses and lower costs.

npx wrangler dev --remote

Test cache Gateway với bookmark Test gateway caching with bookmarks Test cache Gateway ជាមួយ bookmark

curl -X POST http://localhost:8787/bookmarks \
  -H "Content-Type: application/json" \
  -d '{"url":"https://developers.cloudflare.com/workers/","title":"Workers Docs","tags":"docs"}'

curl -X DELETE http://localhost:8787/bookmarks/REPLACE_ID

curl -X POST http://localhost:8787/bookmarks \
  -H "Content-Type: application/json" \
  -d '{"url":"https://developers.cloudflare.com/workers/","title":"Workers Docs","tags":"docs"}'

Bước 4: Xem analytics trên dashboard Step 4: View Analytics in the Dashboard ជំហាន 4: មើល analytics លើ dashboard

Chúng ta đang xây What we're building អ្វីដែលយើងកំពុងសង់

An understanding of the metrics available in the AI Gateway Dashboard.

Vì sao quan trọng Why this matters ហេតុអ្វីសំខាន់

Observability lets you optimize costs, debug issues, and understand usage patterns.

• Request count - Total AI requests routed through the gateway
• Cache hit rate - Percentage served from cache (your cost savings)
• Latency - Average and p99 response times
• Token usage - Input and output tokens consumed
• Error rate - Failed AI requests

Cấu hình rate limit Configure rate limiting កំណត់ rate limit