Hybrid Search
Combining keyword and vector retrieval, then merging the two rankings.
Visão geral
Hybrid search runs a lexical and a semantic query in parallel and fuses the results, usually by reciprocal rank. It solves the problem that each method fails differently: keyword search misses paraphrases, and embedding search misses exact identifiers, names and rare tokens. It exists because the union of the two is more robust than either, which is what most production retrieval actually runs.
Grafo de tecnologias
Como Hybrid Search se liga ao resto do stack.
Usa e depende de
- Embedding concept Techniques Hybrid Search uses Embedding High ✓ source
Aplicado a
- AI Search application Applications Hybrid Search used for AI Search High ✓ source