Model Components
Retrieval Model
Retrieval models rank or select documents from a corpus by their relevance to a query. Sparse retrieval methods (BM25, TF-IDF) use term overlap; dense retrieval methods (DPR, Contriever) use embedding similarity between query and document vectors.
Retrieval models are the search component in RAG systems, determining which content the generative model receives as context. Dense retrieval combined with ANN search in vector databases enables scalable, semantically-aware document retrieval.
Authority Links
Related Terms
Techniques & Methods
Retrieval Augmented Generation (RAG)
An inference-time architecture that retrieves relevant documents from a knowledge base or web index and injects them into a language model's context before generation, grounding answers in real source material.
Techniques & Methods
Semantic Search
Search technology that retrieves results based on the meaning of a query rather than exact keyword matches — using embeddings to represent queries and documents as vectors and finding nearest neighbors in semantic space.
Miscellaneous
Vector Store
Specialized database for storing, indexing, and efficiently retrieving high-dimensional vector embeddings.
Model Components
Embeddings
Dense numerical vectors that represent text, images, or other content in a high-dimensional space where semantically similar items are geometrically close — the foundational data structure for semantic search and RAG retrieval.