Generative AI and LLM glossary

Retrieval

An embedding is a dense vector that represents text, code, or media so similar items land near each other for search and clustering.

machine-learning

A technique for transforming graph-structured data into a continuous vector space while preserving its properties.

Retrieval

Semantic search ranks results by meaning, usually with embeddings, rather than by exact keyword overlap alone.

Retrieval

In AI search, a vector is a list of numbers that locates an item in embedding space so nearby vectors can be retrieved as similar.

Retrieval

A vector database stores embedding vectors and runs similarity search, usually with metadata filters and optional hybrid lexical queries.

Retrieval

Vector search retrieves semantically similar items by comparing embedding vectors rather than relying only on exact keyword overlap.