Multi-vector query #

Executes several vector queries — each targeting a (potentially different) vector field — and fuses their results into one ranking.

Examples #

POST /my-collection/_search
{
  "query": {
    "multi_vector": {
      "queries": [
        { "field": "title_embedding", "query": "search engines", "k": 50 },
        { "field": "body_embedding",  "query": "search engines", "k": 50 }
      ],
      "fusion": "weighted_sum",
      "weights": [2.0, 1.0],
      "k": 10
    }
  }
}

Parameters for multi_vector #

• queries
  (Required, array of vector queries) The individual vector queries to execute.
• fusion
  (Optional) Fusion strategy for combining results:
  • "weighted_sum" — weighted sum of normalized scores; each query’s score is multiplied by its weight (from weights) before summing.
  • {"rrf": {"k": 60}} — Reciprocal Rank Fusion: combines rankings rather than raw scores, with k as the RRF smoothing constant (default 60).
• weights
  (Optional, array of numbers) Per-query weights, must match queries.len() if provided. For WeightedSum: score multipliers; for RRF: rank contribution multipliers. Defaults to equal weight (1.0) per query.
• k
  (Optional, integer, default: 10) Final top-k to return after fusion.