Area 02 · RAG · Concept 02 of 20

Cosine Similarity

Scores how closely two vectors point the same way (1 = same). The usual way to compare embeddings.

01–10 · The basePhase 2 · Weeks 7–10≈ 30 min

The idea

Cosine similarity measures the angle between two vectors, ignoring their length. A score of 1 means the same direction, 0 means unrelated, and negative means opposite. For text embeddings, most real scores fall between about 0.2 and 0.9.

Formula: dot(a, b) / (|a| × |b|). If you normalise vectors to length 1 when you store them, cosine similarity is just the dot product, which is faster. Vector databases offer cosine, dot product and Euclidean (L2) distance; with normalised vectors they rank results the same way.

Scores are relative, not absolute. A 0.62 might be a great match with one model and a poor one with another. Use scores to rank, and tune any cut-off threshold on real examples.

Why it matters

It is the scoring function behind every nearest-neighbour search you will run.

Words to know

  • Dot productSum of pairwise products of two vectors.
  • NormalisationScaling a vector to length 1.
  • Cosine distance1 − cosine similarity; used by some databases.

Try it without code

Do it by hand

  1. Take vectors a = [1, 2] and b = [2, 4].
  2. Compute dot / (lengths). You get 1: same direction.
  3. Try b = [-2, 1] and get 0.

Use it in code

Cosine from scratch and with normalised vectors.

python
import numpy as np

def cosine(a, b):
    return float(np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b)))

a, b, c = np.array([1, 2]), np.array([2, 4]), np.array([-2, 1])
print(cosine(a, b), cosine(a, c))

an = a / np.linalg.norm(a); bn = b / np.linalg.norm(b)
print(float(an @ bn))   # same as cosine once normalised
PRACTICE · TICK IT AFTER THIS

Pick a similarity threshold for "is this a duplicate question?" by scoring 20 labelled pairs and choosing the cut-off with fewest mistakes.

Common mistakes

  • Treating 0.8 as universally "very similar".
  • Using cosine on unnormalised vectors with an index set to dot product.

Go deeper