> ## Documentation Index
> Fetch the complete documentation index at: https://retrievalcontextprotocol.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Glossary

> The retrieval vocabulary RCP models — bi-encoders, late interaction, RRF, MMR, GraphRAG, and more.

RCP is designed backwards from the state of the art in retrieval. These are the
terms that recur across the docs.

| Term                            | Meaning                                                                                                                                                       |
| ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Bi-encoder**                  | Encodes query and document independently into one vector each; fast, approximate (dense retrieval).                                                           |
| **Cross-encoder**               | Jointly encodes a (query, document) pair for one relevance score; accurate, used for reranking.                                                               |
| **Late interaction**            | Multi-vector scoring (MaxSim) that approximates cross-encoder accuracy at bi-encoder speed (ColBERT, ColPali).                                                |
| **Learned-sparse**              | A sparse term→weight vector produced by a model (SPLADE), searchable with an inverted index.                                                                  |
| **Dense / sparse / hybrid**     | Retrieval over dense vectors / lexical or learned-sparse terms / a fusion of both.                                                                            |
| **RRF**                         | Reciprocal Rank Fusion — rank-only list merging robust to incomparable scores. See [Federation](/features/federation).                                        |
| **MMR**                         | Maximal Marginal Relevance — re-ranks for the relevance–diversity trade-off.                                                                                  |
| **HyDE**                        | Hypothetical Document Embeddings — embed an LLM-generated pseudo-answer as the query. See [Query Transform](/methods/query-transform).                        |
| **GraphRAG**                    | Retrieval over a knowledge graph / community summaries (local, global, drift). See [Graph](/methods/graph).                                                   |
| **Agentic RAG**                 | A client-driven reasoning loop that interleaves transform/retrieve/graph steps, optionally threaded by `sessionId`. See [Agentic RAG](/concepts/agentic-rag). |
| **Confidence**                  | A normalised `[0,1]` per-hit relevance/self-eval signal, comparable across calls, that corrective/adaptive systems threshold on.                              |
| **Retrieval unit / level**      | The granularity (chunk…subgraph…page) and abstraction level (RAPTOR depth, Leiden level) of a hit.                                                            |
| **Memory (RCP)**                | A compact global/session structure over a corpus that yields *clues*/entry-points to steer retrieval (MemoRAG, HippoRAG). See [Memory](/methods/memory).      |
| **Feedback**                    | A client→server signal (used/cited/reward/poisonSuspected) RL-trained or corrective retrievers consume. See [Feedback](/methods/feedback).                    |
| **Contextual retrieval**        | Prepending chunk-situating context before embedding/indexing (Anthropic).                                                                                     |
| **Recall stage / rerank stage** | Cheap high-recall candidate generation, then expensive precise reranking. See [the pipeline](/concepts/pipeline).                                             |
| **MaxSim**                      | The late-interaction scoring function: sum over query vectors of the max similarity to any document vector.                                                   |
| **Aggregator**                  | A server that federates downstream engines and advertises [`catalog`](/methods/catalog).                                                                      |
| **Modality**                    | Coarse content kind: text, image, audio, code, multimodal. See [Content blocks](/concepts/message-format#content-blocks-modality).                            |
| **Capability**                  | A feature a server advertises at `initialize`; presence ⇒ supported. See [Capabilities](/concepts/capabilities).                                              |
| **Selector / Federation**       | Client-side routing: pick one live backend, or fan out to all and fuse.                                                                                       |