Problems / RAG and retrieval, medium

Multi-tenant RAG: the permission filter

Each customer may only see its own documents, so every retrieval passes a document-ACL filter after hybrid search. The filter has 2 slots and takes about 60 ms; questions arrive at 60 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 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

60 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 Hybrid search, Document ACL filter, 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
Hybrid searchHybrid searchAI app calls it.Hybrid search combines keyword matching (BM25) with vector similarity.400 slots · 2 steps
Document ACL filterTool policy engineAI app calls it.A policy engine checks each tool call against what this agent, user and data may do.2 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