Hybrid Search
A retrieval architecture that combines keyword search (BM25 or similar) with semantic vector search, blending the two ranked results to capture both exact-match precision and semantic recall.
How it works
Pure semantic search misses documents where the query exact-matches a rare term but is semantically distant. Pure keyword search misses semantically-relevant documents that use different vocabulary. Hybrid search runs both retrievers in parallel and combines the results using reciprocal rank fusion or a learned ranker. For UK enterprise knowledge work (legal precedent search, technical documentation retrieval, clinical-letter retrieval) hybrid search is reliably better than either alone. Implementation typically uses a vector database for the semantic side (pgvector, Qdrant, Weaviate) and Elasticsearch / OpenSearch for the keyword side, with a fusion layer combining results. Ayoob AI deploys hybrid search by default in production RAG systems.
Related terms
Semantic Search
Search that ranks results by meaning rather than exact keyword match, using vector embeddings to retrieve semantically-similar content even when no terms overlap.
Vector Database
A database optimised for storing and querying high-dimensional vector embeddings using approximate nearest-neighbour algorithms, used as the retrieval layer in RAG systems and semantic search.
Retrieval-Augmented Generation (RAG)
An architecture pattern that grounds language model outputs in retrieved documents from a private corpus, reducing hallucination and enabling answers based on the firm's own data rather than the model's training set.
Want to see this technology in action?
Book a Discovery Call