Package io.milvus.v2.service.vector.request.ranker

package io.milvus.v2.service.vector.request.ranker
  • Classes
    Class
    Description
    DecayRanker
    The Decay reranking strategy, which by adjusting search rankings based on numeric field values.
    ModelRanker
    The Model reranking strategy, which transforms Milvus search by integrating advanced language models that understand semantic relationships between queries and documents.
    RRFRanker
    The RRF reranking strategy, which merges results from multiple searches, favoring items that consistently appear.
    WeightedRanker
    The Average Weighted Scoring reranking strategy, which prioritizes vectors based on relevance, averaging their significance.