Problems / RAG and retrieval, medium
A cache in front of the reranker hits 15%, because it is keyed on the raw question text including whitespace and casing.
Free to open. Runs in your browser, no sign-up.
Success ≥ 99%, p99 ≤ 5 s.
320 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 Rerank cache.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s. | 3 replicas × 500 slots · timeout 30 s |
| Rerank cacheTool result cache | AI app calls it.Calls Reranker.Agents often repeat the same read-only tool call within and across tasks. | 5000 slots · 15% hit rate |
| RerankerReranker | Rerank cache calls it.A reranker reads each retrieved passage together with the question and reorders by relevance. | 16 slots |
Try it first. Open one hint at a time if you get stuck.
Normalise the cache key.
Follow one question through each retrieval stage; the stage that turns red is the one to fix first.
Raise the cache hit rate by normalising keys.