cellmap_flow.serving.engine
===========================

.. py:module:: cellmap_flow.serving.engine

.. autoapi-nested-parse::

   Which inference server a process runs: chunkmirage's or the Flask one.

   ``CELLMAP_FLOW_ENGINE`` is ``chunkmirage`` (the default) or ``flask``. Every
   place that starts a server (``cellmap_flow serve``, ``infer --server-check``
   and the finetune loop) builds it with ``make_server``, and both take the
   same arguments.

   A model can run in an environment of its own (its ``env``: a pixi
   environment, an alias or a path), which may not have chunkmirage. Unless
   chunkmirage was asked for, such a server is the Flask one, with a warning;
   the dashboard draws either server's layers.



Attributes
----------

.. autoapisummary::

   cellmap_flow.serving.engine.logger
   cellmap_flow.serving.engine.ENGINE_ENV
   cellmap_flow.serving.engine.ENGINES
   cellmap_flow.serving.engine.DEFAULT_ENGINE


Functions
---------

.. autoapisummary::

   cellmap_flow.serving.engine.engine_name
   cellmap_flow.serving.engine.make_server
   cellmap_flow.serving.engine.check_server


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

.. py:data:: logger

.. py:data:: ENGINE_ENV
   :value: 'CELLMAP_FLOW_ENGINE'


.. py:data:: ENGINES
   :value: ('flask', 'chunkmirage')


.. py:data:: DEFAULT_ENGINE
   :value: 'chunkmirage'


.. py:function:: engine_name(name=None) -> str

   ``name``, else ``CELLMAP_FLOW_ENGINE``, else the default; refused if unknown.


.. py:function:: make_server(dataset_name, model_config, *, engine=None, **kwargs)

   The server for ``model_config`` over ``dataset_name``; ``kwargs`` are
   CellMapFlowServer's (restart_callback, restart_token, resample).


.. py:function:: check_server(server)

   Compute one chunk the way a request would: ``infer --server-check``.