Which metric should I use for embeddings?

Most text-embedding models are tuned for cosine similarity or dot product. If your vectors are normalised to unit length, cosine, dot, and Euclidean rank results identically, so the choice often comes down to what your vector database supports.

What is the difference between Euclidean and Manhattan distance?

Euclidean (L2) is the straight-line distance — the square root of summed squared differences. Manhattan (L1) is the sum of absolute differences. L2 penalises large single-dimension gaps more heavily, while L1 is more robust to outliers.

Why is dot product not bounded?

Unlike cosine similarity, the dot product scales with vector magnitude, so it has no fixed range. Models trained with dot-product objectives use it directly; otherwise normalise first or use cosine.

Is anything sent to a server?

No. Every metric is computed locally in your browser. The vectors you paste are never uploaded or stored.

Vector Distance Suite

Vector distance suite

Different vector databases and embedding models expect different distance functions, and the choice subtly changes which results rank highest. This tool computes the four metrics you actually care about — cosine similarity, dot product, Euclidean (L2) distance, and Manhattan (L1) distance — for the same pair of vectors, so you can compare them at a glance and match your retrieval configuration without writing a script.

How it works

The tool parses both inputs into equal-length number arrays and computes each metric directly:

Cosine similarity — dot product divided by the product of L2 norms; range −1 to 1.
Dot product — sum of element-wise products; unbounded, magnitude-sensitive.
Euclidean (L2) distance — square root of the sum of squared differences.
Manhattan (L1) distance — sum of absolute differences.

It also reports cosine distance (1 − cosine) since many databases express similarity that way. All four update instantly as you edit either vector.

Tips and notes

Normalise to compare fairly. On unit-length vectors, cosine and dot product agree and Euclidean ranking matches cosine — useful for verifying your embeddings are normalised.
Match your store’s metric. Pinecone, Weaviate, pgvector, and FAISS each default to specific metrics; pick the one your index uses to predict its ranking.
Watch magnitude with dot product. If one vector is much longer, dot product can rank it high even when its direction is a poor match.
Local only. Nothing leaves your browser.