LLM Reference
Concepts & capability filters
representation

Embedding

An embedding maps text into a dense vector so semantic similarity becomes distance — the backbone of RAG and semantic search.

Category
representation
Difficulty
Not classified
Aliases
None tracked
Last reviewed
2026-07-02

Key facts

  • Choosing an embedding model is a separate decision from your generation model: weigh retrieval quality on your domain, vector dimensionality (which drives storage and query cost), max input length, and per-token or per-request price across providers.

Models Mentioning Embedding(12)