A precise glossary of retrieval and LLM terminology. One term per page: embedding, chunk, vector index, reranking, context window.https://whatisrag.net/https://whatisrag.net/blogs/context-window/https://whatisrag.net/blogs/context-window/The maximum amount of text, measured in tokens, that a language model can process in a single request — input and output together.Sun, 26 Jul 2026 00:00:00 GMTgenerationcorehttps://whatisrag.net/blogs/reranking/https://whatisrag.net/blogs/reranking/A second scoring pass that reorders an already-retrieved candidate set using a slower, more accurate model that reads query and document together.Sat, 25 Jul 2026 00:00:00 GMTretrievalgenerationhttps://whatisrag.net/blogs/vector-index/https://whatisrag.net/blogs/vector-index/A data structure that stores embeddings and finds the ones nearest to a query vector without comparing against every stored vector.Sat, 25 Jul 2026 00:00:00 GMTindexingretrievalhttps://whatisrag.net/blogs/chunk/https://whatisrag.net/blogs/chunk/A unit of text stored and retrieved as a single item in a retrieval system — the smallest thing a search can return. No standard size exists.Fri, 24 Jul 2026 00:00:00 GMTretrievalcorehttps://whatisrag.net/blogs/embedding/https://whatisrag.net/blogs/embedding/A fixed-length list of numbers representing a piece of text, produced so that texts with similar meanings land near one another in the space.Fri, 24 Jul 2026 00:00:00 GMTembeddingscore