SYS.TOOLS
Embedding Playground
Embedding visualization online: type sentences and watch them cluster by meaning on a live 2D map, with real cosine similarity between texts. No sign-up.
EmbeddingsVector SearchSemantic SearchDeveloper Tool
Last updated
FREQUENTLY ASKED QUESTIONS
What is a text embedding?
A text embedding is a list of numbers (a vector) that represents the meaning of a piece of text. Sentences with similar meanings get vectors that point in similar directions, which is what lets machines compare texts by meaning instead of exact words.
What are text embeddings used for?
Embeddings power semantic search, RAG (retrieval-augmented generation), recommendation systems, clustering, and duplicate detection. Any time an AI system needs to find 'texts that mean roughly the same thing,' embeddings are doing the work.
What is cosine similarity?
Cosine similarity measures how closely two vectors point in the same direction, on a scale where 1 means identical meaning and values near 0 mean unrelated. The lines in this playground show the actual cosine similarity between your sentences.
How is the 2D map made from high-dimensional vectors?
Each sentence is embedded with OpenAI's text-embedding-3-small model, then projected from 256 dimensions down to 2 using PCA (principal component analysis). The projection loses some information, so trust the similarity lines over exact point distances.
Is this embedding visualizer free, and is my text stored?
Yes, it's completely free with no sign-up, up to 30 requests per hour. Your sentences are sent to the embedding model, and nothing is stored on our servers.
