{
  "id": "hybrid-search",
  "code": "PTL-0128",
  "term": "Hybrid Search",
  "aliases": [
    "hybrid retrieval",
    "reciprocal rank fusion",
    "RRF"
  ],
  "category": "retrieval-tools",
  "definition": "Hybrid search combines keyword retrieval, such as BM25, with dense embedding retrieval and merges the two result lists, so that a query benefits from both exact-term matching and semantic matching.",
  "description": "The lists are usually merged by reciprocal rank fusion, which scores each document by the sum of the reciprocals of its ranks in each list and needs no score calibration between systems. Hybrid retrieval followed by a reranker is a common default for RAG pipelines.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "bm25",
    "dense-retrieval",
    "reranking",
    "contextual-retrieval",
    "retrieval-augmented-generation"
  ],
  "introduced": null,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Reciprocal rank fusion outperforms condorcet and individual rank learning methods",
      "authors": "Cormack et al.",
      "year": 2009,
      "url": "https://doi.org/10.1145/1571941.1572114"
    },
    {
      "title": "Introducing Contextual Retrieval",
      "authors": "Anthropic",
      "year": 2024,
      "url": "https://www.anthropic.com/news/contextual-retrieval"
    }
  ],
  "url": "https://protologue.com/t/hybrid-search/",
  "citation": "Protologue. (2026). Hybrid Search. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0128). https://protologue.com/t/hybrid-search/"
}