personalitylinmult.inference.register_models
============================================

.. py:module:: personalitylinmult.inference.register_models

.. autoapi-nested-parse::

   Register the trained FI models into the MLflow Model Registry.

   Reads the best checkpoint each training run logged (under its ``model/`` artifact
   path), wraps it as a ``pyfunc`` model, and registers it under a stable name so it
   can be served or containerised. Run after training; idempotent in the sense that
   re-running adds a new version rather than clobbering the old one.

   .. rubric:: Example

   Register the three audio models (LinMulT fusion + two LinT unimodal arms)::

       uv run python -m personalitylinmult.inference.register_models



Attributes
----------

.. autoapisummary::

   personalitylinmult.inference.register_models.logger
   personalitylinmult.inference.register_models.DEFAULT_TRACKING_URI
   personalitylinmult.inference.register_models.REGISTRATIONS


Classes
-------

.. autoapisummary::

   personalitylinmult.inference.register_models.Registration


Functions
---------

.. autoapisummary::

   personalitylinmult.inference.register_models.register_all
   personalitylinmult.inference.register_models.main


Module Contents
---------------

.. py:data:: logger

   Module-level logger.

.. py:data:: DEFAULT_TRACKING_URI
   :value: 'sqlite:///mlflow.db'


   Where the training runs were logged.

.. py:class:: Registration

   One model to register.

   :param experiment: MLflow experiment holding the trained run.
   :type experiment: str
   :param registered_name: Name to register under, e.g.
                           ``fi_linmult_wavlm-emotion2vec``.
   :type registered_name: str
   :param run_id: Exact run to register. ``None`` falls back to the
                  experiment's most recently *started* run -- convenient while
                  iterating, but not a deliberate choice of "the best run", so a
                  promotion decision should pin this explicitly (see
                  :func:`set_champion` for the separate, deliberate promotion step).
   :type run_id: str | None


.. py:data:: REGISTRATIONS
   :type:  list[Registration]

   LinMulT fusion (wavlm+emotion2vec) plus the two LinT
   unimodal arms (wavlm only, emotion2vec only).

   :type: The audio models

.. py:function:: register_all(registrations: list[Registration] | None = None, tracking_uri: str = DEFAULT_TRACKING_URI) -> dict[str, str]

   Register every configured model, returning ``{name: version}``.

   :param registrations: Models to register; the
                         module default when ``None``.
   :type registrations: list[Registration] | None
   :param tracking_uri: MLflow backend store.
   :type tracking_uri: str

   :returns: Registered name to version.
   :rtype: dict[str, str]


.. py:function:: main() -> None

   CLI entry point.

   With no arguments, registers every model in :data:`REGISTRATIONS`. Passing
   ``--experiment``/``--registered-name`` registers exactly that one model
   instead -- the deliberate, ad hoc path for a run that is not (yet, or
   ever) part of the standing registration list. ``--alias`` additionally
   promotes the newly registered version, so a single command can both
   register and mark a version as the champion.