Is my data private when using Vector Similarity & Distance Calculator?

Yes. Code Station operates completely client-side without external telemetry, uploads, or server proxies. Your data never leaves your device.

Can AI agents use Vector Similarity & Distance Calculator?

Yes. Vector Similarity & Distance Calculator supports browser-native WebMCP (Web Model Context Protocol) and local stdio MCP servers via codestation-mcp for automated workflows.

AI & Prompt Engineering

Vector Similarity & Distance Calculator

Keep this tool in your workbenchReport a problem

Station 25

AI & Prompt Engineering

In-browser token estimation, LLM JSON repair, prompt template interpolation, vector geometries, and pattern builder.

Vector Similarity & Geometry Calculator

Compare embedding vectors using Cosine similarity, Euclidean distance (L2), Dot product, Manhattan distance (L1), angles, and dimensional breakdown.

Vector A (JSON array, comma or space-separated)

Vector B (JSON array, comma or space-separated)

Cosine Similarity

0.9968

99.84% Match

Angle: 4.58° (0.080 rad)

Dimensions6Vector Length

Euclidean (L2)0.1323Straight-line distance

Dot Product1.9112A · B

Manhattan (L1)0.3100Sum of abs deltas

Chebyshev0.0700Max single delta

Norms (||A||, ||B||)1.42, 1.35Magnitudes

Component Contribution Breakdown (Top Dimensions)

Dim #	A[i]	B[i]	Product (A[i] × B[i])	Delta \|A[i] - B[i]\|	Impact
Dim 0	0.3500	0.3100	+0.1085	0.0400	Positive (aligned)
Dim 1	0.7200	0.6900	+0.4968	0.0300	Positive (aligned)
Dim 2	-0.4100	-0.4500	+0.1845	0.0400	Positive (aligned)
Dim 3	0.8800	0.8200	+0.7216	0.0600	Positive (aligned)
Dim 4	0.1200	0.1900	+0.0228	0.0700	Positive (aligned)
Dim 5	-0.6500	-0.5800	+0.3770	0.0700	Positive (aligned)

Loading AI & Prompt Engineering controls…

Browse the AI & Prompt Engineering station →

What does this tool do?

Vector Similarity & Distance Calculator: vector a (json array, comma or space-separated numbers), vector b (json array, comma or space-separated numbers), primary metric → cosine similarity & percentage match, euclidean distance (l2), dot product, manhattan distance (l1), dimensional contribution breakdown. Process locally in your browser. Inputs: Vector A (JSON array, comma or space-separated numbers), Vector B (JSON array, comma or space-separated numbers), Primary Metric. Outputs: Cosine similarity & percentage match, Euclidean distance (L2), Dot product, Manhattan distance (L1), Dimensional contribution breakdown.

How to use it?

Provide the listed input and choose Execute. Review the result, then copy or download where available. Clear removes inputs and results.

Browser-local processing. No uploads, content logging, persistence or remote resource loading. Generated markup is inert text; files are treated as untrusted data.

100% in-browser AI & prompt processing. Token estimation, JSON repair, vector metrics, and prompt construction run entirely in client memory with zero server uploads or external LLM API calls.

Compare embedding vectors using Cosine similarity, Euclidean distance, Dot product, Manhattan distance, angles, and dimensional contribution breakdown.