Similarity
2D map
RAG
Computes the semantic similarity between texts using the paraphrase-multilingual-MiniLM-L12-v2 model, which turns each text into a 384-dimension vector (embedding). Cosine similarity measures how alike they are: 1.0 = identical meaning, 0.0 = unrelated. The model runs 100% in your browser (WebAssembly); no text leaves your device.
A direct similarity score between two texts. Useful for measuring how semantically alike two sentences or paragraphs are.
This tool will download a multilingual AI model (~150 MB) from HuggingFace Hub the first time you use it. The model is stored in your browser and is not downloaded again. No text of yours leaves your device — all processing happens locally.
huggingface.co · *.cdn.hf.co · cdn.jsdelivr.net — only to download the file: nothing of yours is sent.