Problems / RAG and retrieval, easy
Each RAG question writes retrieval traces to an observability API capped at 3,000 a minute, at 80 questions a second.
Free to open. Runs in your browser, no sign-up.
Success ≥ 99%.
80 requests a second for 30 seconds: 100% request (reads).
What each component does in this design, and what calls it. The simulator mimics each one from these settings.
| Component | Its job here | Settings |
|---|---|---|
| Load balancerLoad balancer | Traffic 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 service | Load balancer forwards to it.Calls Agent tracing, Hybrid search, GPU serving pool.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s. | 3 replicas × 500 slots · timeout 30 s |
| Agent tracingAgent tracing | AI app calls it.Agent traces record every model and tool call with inputs, outputs, tokens and timing. | 5000 slots · 3,000 calls/min |
| Hybrid searchHybrid search | AI app calls it.Hybrid search combines keyword matching (BM25) with vector similarity. | 400 slots · 2 steps |
| GPU serving poolSelf-hosted serving pool | AI app calls it.GPU servers batch requests together; throughput rises with batch size until memory runs out. | 800 slots |
Try it first. Open one hint at a time if you get stuck.
80 × 60 = 4,800 a minute.
Follow one question through each retrieval stage; the stage that turns red is the one to fix first.
Raise the tracing quota (send traces asynchronously in production).