FREE STUDY NOTES · AI-103

Vector, hybrid and semantic search in Azure AI Search

Vector fields and profiles, HNSW vs exhaustive KNN, hybrid queries with RRF, and the semantic ranker.

From Ultra Transcenders AI-103 by Tony Rough (publishing soon)

Vector search finds content by meaning rather than exact words, and hybrid search combines it with keyword search. Both depend on how vector fields, algorithms and vectorizers are configured in the index.

Vector fields and the vectorSearch section

HNSW Exhaustive KNN
Result Approximate nearest neighbours Exact, brute force over all vectors
Memory Graph held in memory, uses vector index quota No vector index quota
Suits Most workloads, large data Small or medium data, precision first, ground truth for recall testing
Switch "exhaustive": true per query on an HNSW field Can’t run HNSW queries

Common trap: indexing a field with exhaustiveKnn and planning to query it with HNSW later - only HNSW fields can switch per query, and only to exhaustive.

Vector queries

Hybrid queries

One request carrying search text plus vectorQueries splits into a keyword (BM25) search and a vector (HNSW) search that run in parallel. Reciprocal Rank Fusion merges their results. An optional semantic ranker then reranks the top 50, and the top chunks ground the model's answer; a dashed path skips the ranker.
Figure 12.2: A hybrid query runs keyword and vector search in parallel, merges them with RRF and can rerank the top 50 with the semantic ranker

Get the whole book

This note is one section of Ultra Transcenders AI-103: Developing AI Apps and Agents on Azure, an independent study guide that explains every topic the exam covers by technology, with comparison tables, diagrams and the common traps, plus a glossary linked to Microsoft Learn.

Amazon.co.ukKindle: coming soonPaperback: coming soon
Amazon.comKindle: coming soonPaperback: coming soon

Publishing soon on Amazon in Kindle and paperback editions.

About the book · Free AI-103 glossary · All AI-103 study notes

More AI-103 study notes