AI Concepts category
Retrieval & RAG
Chunking
Chunking divides source content into smaller units that can be indexed, retrieved, and placed in model context.
Embedding
An embedding is a numerical representation that places an input in a learned vector space.
Query Rewriting
Query rewriting reformulates a request so a retrieval system can find more relevant content.
Reranking
Reranking reorders retrieved candidates using a second, usually more expensive relevance step.
Retrieval Top-k
Retrieval top-k is the number of highest-ranked results requested or retained from a retrieval stage.
Retrieval-Augmented Generation (RAG)
RAG retrieves relevant information at runtime and supplies it as context before a model generates an answer.
Vector Database
A vector database stores vectors and metadata and provides indexed similarity search over them.
Vector Search
Vector search finds items whose stored vectors are close to a query vector.