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.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Hybrid search 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.
- Full-text search
Keyword retrieval in Azure AI Search that uses an inverted index with BM25 ranking. It excels at exact matches on names, identifiers and product codes but does not catch paraphrased wording.
- RRF
A Cosmos DB system function, used with ORDER BY RANK, that merges the rankings from VectorDistance and FullTextScore, with optional weights, to give hybrid search results.
- Semantic ranker
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.
Related terms
- File search tool
Gives an agent hybrid search over files users upload: they are parsed, split into 800-token chunks and embedded in a vector store. For an already curated index, use a different tool.