Vector Index Tuning

1---
2name: vector-index-tuning
3description: Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
4---
5 
6# Vector Index Tuning
7 
8Guide to optimizing vector indexes for production performance.
9 
10## Use this skill when
11 
12- Tuning HNSW parameters
13- Implementing quantization
14- Optimizing memory usage
15- Reducing search latency
16- Balancing recall vs speed
17- Scaling to billions of vectors
18 
19## Do not use this skill when
20 
21- You only need exact search on small datasets (use a flat index)
22- You lack workload metrics or ground truth to validate recall
23- You need end-to-end retrieval system design beyond index tuning
24 
25## Instructions
26 
271. Gather workload targets (latency, recall, QPS), data size, and memory budget.
282. Choose an index type and establish a baseline with default parameters.
293. Benchmark parameter sweeps using real queries and track recall, latency, and memory.
304. Validate changes on a staging dataset before rolling out to production.
31 
32Refer to `resources/implementation-playbook.md` for detailed patterns, checklists, and templates.
33 
34## Safety
35 
36- Avoid reindexing in production without a rollback plan.
37- Validate changes under realistic load before applying globally.
38- Track recall regressions and revert if quality drops.
39 
40## Resources
41 
42- `resources/implementation-playbook.md` for detailed patterns, checklists, and templates.
43