inference for updating record embeddings

[davidberenstein1957]

Automatically add predictions to records as they are logged into Argilla. This can be used for making it really easy to pre-annotated a dataset with an existing model or service.

MVP

from argilla_plugins.inference import embedder

embedder(name="dataset", model="model_name", vector_name="vector")
embedder.start()

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