// ⌕ RAG & Vector Retrieval

Sentence Embeddings (Sentence-BERT)

Encodes sentences into vectors compared by cosine similarity.

句向量（Sentence-BERT） 2019 Foundational core

IN PLAIN WORDS

Siamese BERT trained on sentence pairs makes similar sentences close. Precompute document vectors and queries take milliseconds. Most embedding models follow this idea.

Used in: Semantic search, RAG embeddings, clustering

TIMELINE · prerequisites → this → what builds on it

2018 BERT2018 Contrastive L…2019 Sentence Embeddin…2020 Dense Passage…2022 Matryoshka Re…2022 HyDE (Hypothe…

01Original paper

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Nils Reimers, Iryna Gurevych · 2019

arXiv ↗ ✓ Verified · arXiv API

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

Sentence Embeddings (Sentence-BERT)

Then you can learn

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Official docs

sbert.net ↗EN

04Where the course teaches it

U40 Tokenization & Embeddings BPE tokenisation, per-token pricing, embeddings and semantic similarity. 6 h6 algorithms2 paperslesson ready U80 Embeddings, Vector Search & Reranking BM25, sentence embeddings, DPR, ColBERT, HNSW, PQ and hybrid search. 8 h10 algorithms4 papers

On learning paths:AI Application Engineer

For AI / data

Verification: verified, checked 2026-10-21.
JSON: /api/learn/algorithms.json (id: sentence-bert)