This is a general embedding model: It maps any piece of text (e.g., a title, a sentence, a document, etc.) to a fixed-length vector in test time without further training. With instructions, the embeddings are domain-specific (e.g., specialized for science, finance, etc.) and task-aware (e.g., customized for classification, information retrieval, etc.)

The model is easy to use with sentence-transformer library.

Then you can use the model like this to calculate domain-specific and task-aware embeddings:

You can further use the model to compute similarities between two groups of sentences, with customized embeddings.