Words, phrases, or entire documents, as well as images, audio, and other types of data, can all be vectorized.
The goal is that semantically similar data items receive feature vectors close to each other.
[6] Vector databases are also often used to implement retrieval-augmented generation (RAG), a method to improve domain-specific responses of large language models.
The retrieval component of a RAG can be any search system, but is most often implemented as a vector database.
[citation needed] In recent benchmarks, HNSW-based implementations have been among the best performers.