What does cosine similarity actually measure between two embeddings?

Attempt it

Quick reference

TL;DR

Cosine similarity is the cosine of the angle between two vectors, a geometric quantity. It is not a calibrated probability of relevance; that interpretation has to be derived per model.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Picture two arrows pointing out from the same spot. If both point in roughly the same direction, the cosine of the angle between them is close to 1. If one points up and the other points sideways, the cosine is close to 0. That is all cosine is: a way of asking how parallel two arrows are. It does not know whether the two arrows mean similar things in the real world. That extra meaning is something we attach by checking many examples, not something the number tells us on its own. So a high cosine often hints at relatedness, but it is not a built-in promise.

Key concepts

Embeddings Retrieval-augmented generation

Detailed answer & concept explanation

~4 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

2 min: cosine as geometry + formula and unit-norm equivalence with dot product + why it is not a probability + per-model thresholding + top-K plus reranker pattern.

Real-world examples

Real products, models, and research that use this idea.

FAISS, Pinecone, and Weaviate all expose cosine and inner-product metrics. For unit-norm embeddings (the default in OpenAI text-embedding-3 and Voyage-3), the two are equivalent.
Production RAG stacks at Notion, Perplexity, and Cursor pair top-K cosine retrieval with a cross-encoder reranker so absolute cosine never gates user-visible behavior.
Cohere rerank-3.5 and Voyage rerank-2.5 in 2026 are the most common cross-encoder rerankers paired with bi-encoder embedding cosine retrieval.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow is cosine similarity related to Euclidean distance for unit-norm vectors?

Sign in or go Pro to see the approach for this follow-up.

QWhen does cosine fail to capture semantic similarity?

Sign in or go Pro to see the approach for this follow-up.

QWhy do most production stacks combine cosine retrieval with a reranker?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Treating cosine as a probability of semantic equivalence and reading 0.8 as 'definitely relevant' on any embedding model.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.