Optimizes vector search performance and resource efficiency for production-scale LLM applications.
This skill provides expert guidance for fine-tuning vector indexes to achieve the ideal balance between search latency, memory consumption, and recall accuracy. It includes automated templates for benchmarking HNSW parameters, implementing advanced quantization strategies like Scalar, Product, and Binary quantization, and configuring high-performance vector databases like Qdrant. Whether you are scaling to millions of vectors or optimizing a local RAG system, this skill provides the mathematical models and implementation patterns needed to ensure your vector infrastructure is production-ready.
