Skip to content
50FiftyPage

Glossary: RAG Basics

all-MiniLM-L6-v2

Also written: MiniLM, sentence-transformers/all-MiniLM-L6-v2

A small sentence-embedding model that turns chunks and questions into 384-number vectors so they can be compared by meaning. It reads at most 256 tokens of text, and anything past that is ignored.

Where the book teaches it

Related terms

EmbeddingTokenizersentence-transformers