Glossary term
Hybrid search
Combining keyword-based and vector-based retrieval, then merging and re-ranking the results.
Keyword search such as BM25 excels at exact terms; vector search excels at paraphrase. Hybrid search runs both and merges results, for example with reciprocal rank fusion.
A re-ranking model often reorders the merged list to put the most relevant passages first.
Related terms
- EmbeddingA numerical vector representing the meaning of text, images or other data, so that similar items have nearby vectors.
- Re-rankingA second retrieval stage in which a more precise model reorders candidate passages by relevance to the query.
- Retrieval-augmented generation (RAG)A pattern in which relevant passages are retrieved from a body of content and given to a language model to ground its answer.
Turning concepts into a working system?
We help teams choose the right pattern and build it with evaluation from day one.