Problems / AI systems, medium

RAG at twice the traffic

Your support assistant doubles to 80 questions a second. The model’s token quota does not.

Solve it in the labTake it as a mock interview

Unlock it once for 15 credits; everything inside it is free (runs, changes, Submit, results, hints). Sign in with Google to start; new accounts get free credits.

Your goals

Success ≥ 99%, time to first token p99 ≤ 1.5 s.

Test cases

Like a coding problem, a solution has to pass every case, not just the one it was built for. Submit in the lab runs all 6; 2 of them are hidden until then.

  1. As given. The problem’s own traffic, scheduled failures and seed.
  2. Peak hour. 25% more traffic than the problem states, with the same failures.
  3. A slow dependency. The main data store or model answers twice as slowly for part of the run.
  4. A server dies. One replica of the service with the most replicas is killed for part of the run.

The traffic

80 requests a second for 30 seconds: 100% question (reads).

The system

What each component does in this design, and what calls it. The simulator mimics each one from these settings.

ComponentIts job hereSettings
Load balancerLoad balancerTraffic enters here.Calls AI gateway.Layer 4 balancers route by IP and port; layer 7 balancers read HTTP and can route by path or header.–
AI gatewayApp serviceLoad balancer forwards to it.Calls Semantic cache (checked first), Embedding model, Vector DB, LLM endpoint.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s.3 replicas × 200 slots · timeout 30 s
Semantic cacheSemantic cacheAI gateway checks it first.A semantic cache matches questions by meaning using embeddings, not exact text.25% hit rate
Embedding modelEmbedding modelAI gateway calls it.Embeddings turn text into vectors where similar meanings sit close together.–
Vector DBVector DBAI gateway calls it.Approximate indexes like HNSW trade a little recall for much faster search.–
LLM endpointLLM endpointAI gateway calls it.Latency has two parts: time to the first token, then a steady stream of tokens per second.300 streams · 6M input tokens/min

More ai systems problems