cellmap_flow.dashboard.services.launch
======================================

.. py:module:: cellmap_flow.dashboard.services.launch

.. autoapi-nested-parse::

   Start the models picked on the Models tab, and show each in the viewer.

   - ``update_run_models()``: stop and forget the models no longer picked,
     start the ones newly picked, each in its own thread. A finetune job's
     server is the Finetune tab's to stop, never this one's.
   - ``run_model()`` / ``run_hf_model()`` / ``run_bioimage_model()`` /
     ``run_cellpose_model()``: start one catalog, Hugging Face, BioImage Model
     Zoo or Cellpose model's inference server (``start_hosts``, which records
     the job) and add its layer, the one Submit would give it. Each is served
     from its type's ``default_env``, when the type sets one
     (``serving.launch.server_argv_for``): a zoo model from pixi's
     ``bioimageio`` environment, a Cellpose one from ``cellpose4``.



Attributes
----------

.. autoapisummary::

   cellmap_flow.dashboard.services.launch.logger
   cellmap_flow.dashboard.services.launch.CELLPOSE_MODELS


Functions
---------

.. autoapisummary::

   cellmap_flow.dashboard.services.launch.run_model
   cellmap_flow.dashboard.services.launch.run_hf_model
   cellmap_flow.dashboard.services.launch.run_model_config
   cellmap_flow.dashboard.services.launch.bioimage_job_name
   cellmap_flow.dashboard.services.launch.run_bioimage_model
   cellmap_flow.dashboard.services.launch.cellpose_job_name
   cellmap_flow.dashboard.services.launch.run_cellpose_model
   cellmap_flow.dashboard.services.launch.running_names
   cellmap_flow.dashboard.services.launch.kill_n_remove_from_neuroglancer
   cellmap_flow.dashboard.services.launch.update_run_models


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

.. py:data:: logger

.. py:function:: run_model(model_path, name, st_data)

.. py:function:: run_hf_model(repo, name, st_data)

   Run a Hugging Face model by repo ID.


.. py:function:: run_model_config(model_config, st_data)

   Run a model given as its config (an entry the Models tab's Add built),
   in its environment, as Submit runs the catalog's.


.. py:function:: bioimage_job_name(key: str) -> str

   A zoo model's job, layer and config name, from the key it is loaded
   by: "affable-shark" is affable_shark. A DOI's slash and dots go too.


.. py:function:: run_bioimage_model(params, st_data)

   Run a BioImage Model Zoo model: ``params`` are its BioModelConfig
   arguments, name included (``bioimage_catalog.bioimage_entry``).


.. py:data:: CELLPOSE_MODELS

.. py:function:: cellpose_job_name(model: str, output: str) -> str

   A Cellpose model's job, layer and config name: "cpsam_v2" serving all
   its channels (flows, the default) is cellpose_sam_v2, its probability
   alone cellpose_sam_v2_probability and its masks cellpose_sam_v2_masks.

   The output is in the name, so one model's outputs can run side by side
   (the probability to look at, the masks to proofread), each its own job
   and layer; the default output keeps the plain name. The voxel size and
   the slice linking are not: changing them restarts that job instead
   (``update_run_models``), rather than leaving the old one running beside.


.. py:function:: run_cellpose_model(params, st_data)

   Run a Cellpose model: ``params`` are its CellposeModelConfig
   arguments, name included (``_cellpose_params``).


.. py:function:: running_names() -> set

   The models running, or on their way: the session's jobs and the
   launches not finished yet.


.. py:function:: kill_n_remove_from_neuroglancer(jobs, s)

   Kill ``jobs`` and drop their layers from the viewer state ``s``.


.. py:function:: update_run_models(names: List[str], hf_repos: List[str] = None, bioimage_models: List[dict] = None, cellpose_models: List[dict] = None)

   Run ``names`` (catalog models), ``hf_repos``, ``bioimage_models``
   ({"id", "voxel_size"} each) and ``cellpose_models`` ({"model",
   "voxel_size", "output", "stitch_threshold"} each), and stop every other
   model. A ValueError, before anything changes, when a zoo model needs a
   voxel size or a Cellpose model's settings are missing or wrong.