`paraphrase` text of less represented records

[David Berenstein]

Automatically paraphrase text from records that are less represented within the entire dataset.

MVP

from argilla_plugins.inference import paraphraser.

paraphraser(name="dataset", model="model_name", vector_name="vector", sim_threshold=0.9)
paraphraser.start()

Stretch
filtering variables like query could be added to limit the sync.