Feature of Azure AI Search that uses Bing-derived language models to re-order the leading BM25 or hybrid results, optionally adding answers and captions. Relevance improves with no change to embeddings.
Also called semantic ranking.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Semantic ranker in context, with comparison tables and the common traps.
Terms in this definition
- Azure AI Search
Managed Azure service that builds indexes over your content and answers keyword, vector, hybrid and semantically ranked queries, optionally with AI enrichment. Retrieval-augmented generation, Foundry agents and knowledge mining all use it to fetch relevant content.
- BM25
Full-text ranking function that weighs how often a term occurs, how rare it is across the corpus and how long each document is.
- Embeddings
Vectors of numbers encoding what text means, placing related content close together as judged by cosine similarity. Switching model or vector size requires embedding all content again.
Related terms
- Hybrid search
One Azure AI Search request that performs vector and full-text search side by side and combines the results through Reciprocal Rank Fusion. Adding the semantic ranker yields the best relevance overall.
- Top-k
The count of nearest-neighbour results (k) returned by a vector query. Microsoft recommends a k of 50 when using semantic ranker, so it has the most input to work with.