Hybrid Search

Hybrid search runs dense and sparse engines in parallel and merges the results:

dense understands semantics but misses keywords;
sparse matches exactly but doesn’t understand synonyms.

Merging is normalized weighted sums or RRF (Reciprocal Rank Fusion, uses only ranks).

Then neural cross-encoder re-ranking: query and document are fed together, the model compares word-by-word – slower but much more accurate than bi-encoder.

No single strategy is reliable in all scenarios on its own.