Problems / RAG and retrieval, medium

Multimodal RAG: the vision encoder

Questions about PDFs with charts and scanned tables send each page image through a vision encoder before retrieval. The encoder has 20 slots and takes about 0.7 s per image; 40 questions arrive a second.

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 ≤ 2.5 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 5; 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 server dies. One replica of the service with the most replicas is killed for part of the run.

The traffic

40 requests a second for 30 seconds: 100% request (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 app.Layer 4 balancers route by IP and port; layer 7 balancers read HTTP and can route by path or header.–
AI appApp serviceLoad balancer forwards to it.Calls Vision encoder, Model.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s.3 replicas × 500 slots · timeout 30 s
Vision encoderImage generation modelAI app calls it.Image generation takes seconds per image and runs on GPUs.20 slots
ModelLLM endpointAI app calls it.Latency has two parts: time to the first token, then a steady stream of tokens per second.2000 streams

More rag and retrieval problems