Travel Itinerary Retrieval Architecture: Node.js 3-Tier Latency Budgets for Planner RAG A developer outlined a three-tier retrieval architecture for a travel-planner RAG system built on Node.js, enforcing a 300 ms p95 retrieval deadline split across lexical filtering, vector search, and reranking. The design propagates a single absolute deadline through each stage rather than per-stage timeouts, returns partial results early when the budget is exhausted, and caps fan-out at two shards with 60 lexical and 40 vector hits to limit merge and rerank load. The developer also recommends storing source revision and fetched-at timestamps alongside chunks so stale policy pages are filtered before ranking. Short answer: give itinerary retrieval a 300 ms p95 contract, spend most of it on one high-recall pass, and reserve a small, explicit slice for reranking and context assembly. A travel planner feels slow when every candidate gets an expensive semantic lookup, so the architecture should narrow the set before it asks for richer signals. Start with a deadline that the product can defend. For a B2B SaaS planner that watches travel policy pages and turns them into trip options, I use 300 ms p95 for retrieval, separate from model generation. That is a budget, not a benchmark claim. Your mileage may vary when the source corpus is remote or freshly indexed. The request carries a destination, dates, traveler constraints, and a change token from the last itinerary. A cheap lexical filter removes stale or impossible documents. A vector pass then retrieves a few dozen candidates. A reranker scores that short list, and a context builder clips passages to the model's input limit. Each stage returns its elapsed time and candidate count; the caller can make a deliberate fallback when a slice is gone. Here is a small Node.js skeleton. It uses generic HTTP boundaries so the same contract works with a self-hosted index or a managed service. type Budget = { deadlineMs: number; spentMs: number }; type Candidate = { id: string; text: string; score?: number }; const elapsed = start: number = performance.now - start; async function retrieveItinerary query: string, budget: Budget : Promise