Embedding Playground

Put in up to five texts and get the similarity between every pair. A sentence transformer runs in this tab and turns each one into 384 numbers; comparing meaning is then just comparing directions. Nothing is uploaded — the model downloads once and everything after that happens on your machine.

Read the explainer: how AI search turns your page into 384 numbers →

TEXTS → SIMILARITY

every pair scored in this tab · nothing uploaded

model: Xenova/all-MiniLM-L6-v2
dimensions: 384 · dtype: q8

01TEXTS

3/5 · two minimum

02SIMILARITY

1.000 on the diagonal is each text against itself

Cosine similarity between every pair. 1.000 on the diagonal is each text against itself.
	1	2	3
1	1.000	0.614	0.094
2	0.614	1.000	0.058
3	0.094	0.058	1.000

The JSON this exports

{
  "model": "Xenova/all-MiniLM-L6-v2",
  "revision": "751bff37182d3f1213fa05d7196b954e230abad9",
  "dtype": "q8",
  "dimensions": 384,
  "texts": [
    "How do I reset my password?",
    "I forgot my login",
    "Our pricing starts at $9 a month"
  ],
  "similarity": [
    [
      1,
      0.614,
      0.094
    ],
    [
      0.614,
      1,
      0.058
    ],
    [
      0.094,
      0.058,
      1
    ]
  ]
}