Function hybrid_candidates

knowledge/hybrid-retrieval/utils/fusion.py:21–29

(
    query: str,
    bm25: BM25Retriever,
    dense: DenseRetriever,
    candidate_k: int = 50,
)

def hybrid_candidates(
    query: str,
    bm25: BM25Retriever,
    dense: DenseRetriever,
    candidate_k: int = 50,
) -> list[tuple[str, float]]:
    bm25_ids = [doc_id for doc_id, _ in bm25.search(query, k=candidate_k)]
    dense_ids = [doc_id for doc_id, _ in dense.search(query, k=candidate_k)]
    return reciprocal_rank_fusion([bm25_ids, dense_ids])[:candidate_k]