Skip to main content

Embeddings & Retrieval

Dense and sparse embeddings, quantization, and vector search for semantic retrieval.

  • IR
  • 19 concepts
Browse all 19 concepts

Representations

Understand what an embedding represents and how a text becomes one vector.

Starting knowledge: Vectors, dot products and basic text processing

Select a concept. Explore its connections, or open the full explanation.

Previewing Dense embeddings.

From meaning to a sentence vector

Explore similarity in an embedding space, then see how token vectors are pooled into a representation of the whole text.

  1. From meaning to a sentence vector

    Dense embeddings

    Connect vector geometry, cosine similarity and learned representations to semantic search.

    Read concept
    1–3 of 8

Lines show suggested reading within a branch. Connections offer optional ways to explore; they are not a checklist of prerequisites.

All Embeddings & Retrieval Concepts

Mastodon