Skip to content
Human Capital Sense

Learning path · Embeddings & Representation · 37

Vector Databases

Storage engines optimized for approximate nearest-neighbor search over millions of embeddings with metadata filters.

Why it matters

  • Operational home for RAG indexes and agent memory.
  • Filter support (tenant, ACL, date) is as important as raw speed.
  • Index parameters affect recall and rebuild cost.

Key ideas

  • ANN indexes
  • Metadata filtering
  • Sharding and replication

Top resources

  1. 01DocsPinecone

    Understanding embeddings

    Why this resource. Why you store vectors at all, before product names.

    Covers in this concept

    • ANN
    • indexes
  2. 02DocsPinecone

    Hybrid search

    Why this resource. How a vector store participates in hybrid retrieval.

    Covers in this concept

    • metadata filters
    • sparse + dense

Video

Vector databases—Pinecone, Weaviate, pgvector, and others—host embedding indexes with hybrid query APIs. Choose based on filter complexity, ops model, and consistency needs. Plan for reindex jobs when embedding models change. Treat collections as part of your data plane: backups, ACL sync, and deletion workflows must match source systems. Practice disaster recovery drills including full reindex from source systems; vector snapshots alone are useless without ingestion pipelines.

Updated 2026-08-09 · Full learning path