name:vector-index-tuningdescription:Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
Vector Index Tuning
Guide to optimizing vector indexes for production performance.
Use this skill when
Tuning HNSW parametersImplementing quantizationOptimizing memory usageReducing search latencyBalancing recall vs speedScaling to billions of vectorsDo not use this skill when
You only need exact search on small datasets (use a flat index)You lack workload metrics or ground truth to validate recallYou need end-to-end retrieval system design beyond index tuningInstructions
Gather workload targets (latency, recall, QPS), data size, and memory budget.Choose an index type and establish a baseline with default parameters.Benchmark parameter sweeps using real queries and track recall, latency, and memory.Validate changes on a staging dataset before rolling out to production.Refer to resources/implementation-playbook.md for detailed patterns, checklists, and templates.
Safety
Avoid reindexing in production without a rollback plan.Validate changes under realistic load before applying globally.Track recall regressions and revert if quality drops.Resources
resources/implementation-playbook.md for detailed patterns, checklists, and templates.