{
  "id": "vector-database",
  "code": "PTL-0124",
  "term": "Vector Database",
  "aliases": [
    "vector store",
    "vector index",
    "vector search"
  ],
  "category": "retrieval-tools",
  "definition": "A vector database stores embeddings alongside their source content and metadata and answers queries by finding the stored vectors nearest to a query vector, usually with approximate nearest-neighbor search.",
  "description": "Exact nearest-neighbor search becomes slow at millions of vectors, so vector databases use index structures such as HNSW graphs or quantized inverted indexes that trade a little recall for large speedups. Most also support metadata filtering and, increasingly, keyword search for hybrid retrieval. A vector index library such as FAISS provides the search without the database features.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "embedding",
    "dense-retrieval",
    "hybrid-search",
    "retrieval-augmented-generation"
  ],
  "introduced": null,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs",
      "authors": "Malkov and Yashunin",
      "year": 2016,
      "url": "https://arxiv.org/abs/1603.09320"
    },
    {
      "title": "Billion-scale similarity search with GPUs",
      "authors": "Johnson et al.",
      "year": 2017,
      "url": "https://arxiv.org/abs/1702.08734"
    }
  ],
  "url": "https://protologue.com/t/vector-database/",
  "citation": "Protologue. (2026). Vector Database. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0124). https://protologue.com/t/vector-database/"
}