A vector is an ordered list of numbers used to represent a point in a high-dimensional space.

Semantic similarity measures how close two pieces of content are in meaning, typically by comparing their embeddings.

Vector search finds the most similar items to a query by comparing embeddings instead of matching exact keywords.

A vector database stores embeddings and is optimized for fast similarity search at scale.

Retrieval is the step of finding the most relevant pieces of content for a given query before generation.

Query transformation rewrites or expands a user's query before retrieval to improve the chances of finding relevant results.

Chunking splits documents into smaller pieces so they can be embedded and retrieved effectively.

Hybrid search combines vector similarity with traditional keyword search to improve retrieval quality.

Metadata is structured information attached to a chunk, such as source or date, used to filter or organize retrieval results.

Reranking reorders an initial set of retrieved results using a more precise model to surface the most relevant ones first.

Retrieval-Augmented Generation retrieves relevant external information and provides it to a language model as context before generating a response.

RAG evaluation measures retrieval quality and answer accuracy to check whether a RAG system is actually helpful.