Embeddings

Dense vector representations of text (or other data) produced by an encoder model. Each token or passage is projected into a high-dimensional space where sem…

Embeddings

Dense vector representations of text (or other data) produced by an encoder model. Each token or passage is projected into a high-dimensional space where semantic similarity corresponds to geometric proximity. Core primitive for retrieval-augmented generation (RAG), semantic search, and re-ranking pipelines.

See also: Contextual Retrieval, BM25, Reranking, Wiki Indexing Pipeline

Stub — expand when a dedicated source is ingested.

Linked pages

• BM25
• Contextual Retrieval
• Reranking