Vector Databases

Purpose: Pick the right vector store, configure it for production, and avoid the failure modes that wreck retrieval quality.

When to Use This Skill

• Choosing a vector store (existing infra reuse vs purpose-built)
• Sizing index, picking distance metric, configuring HNSW/IVF/DiskANN parameters
• Implementing hybrid search (keyword + vector) with reranking
• Adding metadata filters, namespaces, multi-tenancy
• Operating at scale (sharding, replication, cost)

Selection Decision Tree