Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
When tuning HNSW parameters, selecting quantization strategies, optimizing vector index memory/latency, or scaling vector search to billions of vectors.
A tuned vector index balancing recall, latency, and memory; concrete config guidance and benchmark practices for production-scale semantic search.
Use Cases
A team builds a RAG system with 5M documents and sees high memory cost and slow queries. They invoke this skill to choose HNSW + INT8 quantization, tune M and efSearch using the provided tables, and cut memory by 4x while keeping 95% recall. The skill prevents over-optimization and gives a clear tuning path.
An engineer must scale semantic search from 1M to 200M vectors. Using the skill's size-based guidance, they adopt IVF + PQ, plan tiered storage and reindexing, and benchmark with real queries. Result is a cost-efficient, low-latency infrastructure ready for billion-scale growth.
Skill Relationships
Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.
Tier 1 · These Skills Use Me
Tier 2 · Current Skill
Tier 3 · I Use These Skills
Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.
Skill File
