Retrieval Glossary
Browse 16 retrieval terms defined in plain English, from the cultural dictionary of computing.
16 Retrieval Terms
- AI Index
- An index built to support AI workflows, often by storing embeddings, metadata, or searchable representations that help with retrieval and grounding. AI indexes...
- AI Search
- Search functionality enhanced by AI techniques such as semantic ranking, embeddings, query rewriting, or answer generation. AI search is often designed to...
- Approximate Nearest Neighbor
- A similarity search method that trades exact recall for much faster lookup in high-dimensional vector spaces. It influences how models are trained, evaluated,...
- Context Stuffing
- The practice of adding too much material to a prompt or context window in the hope that more information will improve the answer, often with diminishing...
- Dense Retrieval
- A search approach that retrieves items by comparing learned dense embeddings rather than sparse term overlap. It influences how models are trained, evaluated,...
- Dual Encoder
- A retrieval architecture that encodes queries and documents separately for fast vector similarity search. It influences how models are trained, evaluated, or...
- Matryoshka Embeddings
- Embeddings designed so truncated lower-dimensional prefixes still retain useful semantic information, making one vector usable at multiple dimensionalities.
- Needle in a Haystack Test
- A test that checks whether a model can find and use a small relevant fact buried inside a long context window.
- RAG
- Retrieval-Augmented Generation — a technique that enhances LLM responses by first retrieving relevant documents from an external knowledge base and including...
- RAG Retriever
- The retriever component in a retrieval-augmented generation system that selects candidate documents or chunks for the model to use as context. Retriever...
- Relevance Score
- A score used to estimate how relevant a document, chunk, or answer is to a query or task. Relevance scores are common in search, retrieval, and reranking...
- Retrieval Augmented Generation
- A pattern where a model first retrieves relevant documents or facts and then uses them while generating an answer.
- Retrieval Model
- A model used to retrieve relevant information, often by creating embeddings, ranking candidates, or estimating semantic similarity. Retrieval models are...
- Retrieval Pipeline
- The pipeline that turns a query into retrieved evidence, often including rewriting, embedding, search, ranking, filtering, and context assembly. Retrieval...
- Retrieval Quality
- How well a retrieval system finds the right information for a given query, considering relevance, freshness, completeness, and ranking order. Retrieval quality...
- Retriever
- The component in a search or RAG system that fetches candidate information relevant to a query. Retrievers may use embeddings, keywords, hybrid search, or...
Related Topics
- Ai (9 terms in common)
- Search (3 terms in common)
- Embeddings (3 terms in common)
- Architecture (2 terms in common)
- Rag (2 terms in common)
- Models (1 terms in common)
- Components (1 terms in common)
- Ranking (1 terms in common)
- Representation Learning (1 terms in common)
- Vectors (1 terms in common)
- Quality (1 terms in common)
- Llms (1 terms in common)
- Pipelines (1 terms in common)
- Knowledge (1 terms in common)
- Indexing (1 terms in common)
- Prompting (1 terms in common)
- Context Windows (1 terms in common)
- Evaluation (1 terms in common)