What does this tool do?

It compares vectors with calculateVectorSimilarity: JSON or line-based input via parseVectors, cosine/euclidean/dot metrics in a square n x n matrix, plus first-two or deterministic PCA projection via projectVectors.

What happens with mismatched dimensions or zero vectors?

Mismatched dimensions return an explicit same-dimensions error with an empty matrix; a zero vector reports cosine 0 with a warning that the score is undefined.

Is my vector data uploaded or stored?

No. Parsing, similarity math, and PCA all run locally in your browser.

Why is the matrix square instead of unique pairs?

The matrix includes the full n x n grid with the diagonal, so for 4 vectors you read C(4,2) = 6 unique off-diagonal pairs out of 16 cells.

Vector Similarity Calculator

Compare embedding vectors locally with similarity matrices and a 2D projection

Vector editor

MetricProjection

Use JSON arrays or one comma-separated vector per line. Every vector must have the same dimension.

	v1	v2	v3	v4
v1	1.0000	0.9701	0.0000	-1.0000
v2	0.9701	1.0000	0.2425	-0.9701
v3	0.0000	0.2425	1.0000	0.0000
v4	-1.0000	-0.9701	0.0000	1.0000

About

Paste JSON arrays or comma-separated vectors to calculate pairwise metrics and inspect a 2D projection. All calculations run locally with no API calls.

About this tool

Compare vectors with cosine similarity, Euclidean distance, and dot product matrices, plus a deterministic PCA scatter plot in your browser. Vector Similarity Calculator runs in the browser on DevTools. There is no signup, and your input stays on this device unless the tool explicitly performs a live network lookup.

What this tool does not do

Vector Similarity Calculator is a free in-browser utility, not a hosted API. It does not keep server-side history and is not a substitute for production verification in your own stack.

How do I use this tool?

How do I use Vector Similarity Calculator?
Open Vector Similarity Calculator, enter or paste your input, and copy the result. The page works without an account.

RAG Chunking, Embeddings, Evals & SSML: AI App Stack

Visualize RAG chunking strategies, compare embedding similarity, validate fine-tune JSONL, generate needle-in-a-haystack tests, and build valid SSML.

.env Secret Safety Linter

Validate .env syntax and spot likely leaked credentials or placeholder secrets.

.htaccess Generator

Build an Apache .htaccess — HTTPS redirects, rewrites, error pages, security headers, and basic auth

2D Fluid Dynamics & Particle Physics Sandbox

A physics playground with two engines sharing one canvas. The fluid mode runs a real Eulerian Navier-Stokes solver — semi-Lagrangian advection, explicit diffusion, Jacobi pressure projection and vorticity confinement — that you paint with dye and velocity using mouse or touch. The particle mode is a damped Verlet N-body engine with gravity wells, Coulomb attractors and repulsors, spring links, wall restitution and elastic circle collisions. Particle counts adapt to the device (100k target on WebGL2 desktop, 2k-5k on CPU fallback), and every configuration exports as runnable code: a Matter.js world, a PixiJS ticker setup, or a standalone vanilla Canvas engine.

AI Function Calling Schema Generator

Generate function calling JSON schemas from TypeScript interfaces

Algorithm Arena & Data Structure Visualizer

Interactive arena for algorithms and data structures: eight sorting algorithms racing on one seeded input, six pathfinding algorithms walking generated mazes, and BST, AVL, Red-Black, B-tree, heap and trie operations replayed step by step with rotations highlighted. Every run shows the Big-O table and the phase-highlighted reference implementation in four languages, and compared values can be played as pitch (sonification) through the shared audio engine. Everything runs client-side; inputs never leave the browser.

Ansible Playbook Generator

Build an Ansible playbook — hosts, vars, and tasks with modules — as YAML