Searching embeddings for similar meaning, so paraphrases are found via nearest-neighbour algorithms like HNSW; exact identifiers, however, may be missed.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Vector search in context, with comparison tables and the common traps.
Terms in this definition
- 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.
- LIKE
Compares strings with a pattern that can contain the % and _ wildcards. Because it only understands character patterns, searching big volumes of text this way is much slower than using full-text search.
- HNSW
Graph-structured index for approximate vector search in RediSearch and pgvector. Compared with IVFFlat, recall versus speed is better, though building takes longer and memory use is higher.
Related terms
- ANN
Short for approximate nearest neighbour: a vector search that finds most of the closest matches rather than guaranteeing every one, trading completeness for speed and lower cost. DiskANN and HNSW indexes work this way, whereas flat search is exact.
- Cosine similarity
Scores how semantically close two embedding vectors are by the angle between them; vector search relies on it.
- Hybrid search in T-SQL
Combines keyword and meaning-based results by running a vector search alongside a full-text query (CONTAINSTABLE or FREETEXTTABLE) on the same data, then merging the two rankings, usually with Reciprocal Rank Fusion.
- Recall
A measure of approximate (ANN) vector search accuracy: what fraction of the true nearest neighbours, as found by an exact kNN search, the approximate search returned. A value of 1 means nothing was approximated.
- RediSearch
A Redis module for Azure Managed Redis that provides secondary indexes plus full-text and vector search. It can only be turned on when the cache is created and needs Enterprise clustering with the NoEviction policy.
- Semantic caching
A pattern, in an application or gateway, that returns a previous LLM answer when a new prompt means much the same thing, using RediSearch vector search. Azure Managed Redis doesn't offer it as a feature in its own right.
- Vector index
An entry in a Cosmos DB indexing policy, of type flat, quantizedFlat or diskANN, that makes VectorDistance searches faster. It can't be changed once created and needs the vector search feature turned on.