cellmap_flow.ai_annotate.backends.vertex_gemini
===============================================

.. py:module:: cellmap_flow.ai_annotate.backends.vertex_gemini

.. autoapi-nested-parse::

   Gemini image models on Google Cloud Vertex AI, asked to paint the structure.

   The plane is sent as a PNG at its own size (padded to a square when it is
   not one, see ``_square``) with the recolor prompt; the
   model answers with an image in which the structure is painted the prompt's
   colour on black, and the mask is the pixels of that colour. The plane is
   not upsampled first: gemini-3-pro-image charges the same ~560 tokens for an
   image whatever its size, so more pixels buy nothing, and the resolution the
   prompt states must be the one sent.

   Authentication is Application Default Credentials (``gcloud auth
   application-default login``, or a service account on a cloud host), found
   by the SDK, or the credentials file the config names (``credentials_file``,
   read by ``secrets.load_google_credentials``), so this backend holds no key. The google-genai SDK is
   imported only when the first call is made, so the dashboard runs without it
   when the feature is off.

   Every call has a timeout. Only "try again later" answers (429, 503) are
   retried, at most ``MAX_ATTEMPTS`` times in all with bounded waits; anything
   else fails at once. Failures become ``AIAnnotateError`` with a message
   written here: the SDK's text goes to the server log, not the browser.



Attributes
----------

.. autoapisummary::

   cellmap_flow.ai_annotate.backends.vertex_gemini.logger
   cellmap_flow.ai_annotate.backends.vertex_gemini.MAX_ATTEMPTS
   cellmap_flow.ai_annotate.backends.vertex_gemini.RETRY_WAITS_S
   cellmap_flow.ai_annotate.backends.vertex_gemini.RETRY_CODES
   cellmap_flow.ai_annotate.backends.vertex_gemini.RETRY_STATUSES
   cellmap_flow.ai_annotate.backends.vertex_gemini.MAX_REPLY_CHARS


Classes
-------

.. autoapisummary::

   cellmap_flow.ai_annotate.backends.vertex_gemini.VertexGeminiBackend


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

.. py:data:: logger

.. py:data:: MAX_ATTEMPTS
   :value: 3


.. py:data:: RETRY_WAITS_S
   :value: (10.0, 30.0)


.. py:data:: RETRY_CODES
   :value: (429, 503)


.. py:data:: RETRY_STATUSES
   :value: ('UNAVAILABLE', 'RESOURCE_EXHAUSTED')


.. py:data:: MAX_REPLY_CHARS
   :value: 200


.. py:class:: VertexGeminiBackend(project, location, timeout_s, sleep=time.sleep, client_factory=None, credentials_file=None)

   Recolor-and-threshold segmentation through Vertex AI.

   ``project`` may be None, in which case the SDK takes it from
   ``GOOGLE_CLOUD_PROJECT`` or the credentials. ``credentials_file`` may be
   None, in which case the SDK finds Application Default Credentials
   itself. ``sleep`` is how retries
   wait and ``client_factory`` (no arguments, returns an object with
   ``.models.generate_content``) replaces the SDK client; both are for tests.


   .. py:attribute:: project


   .. py:attribute:: credentials_file
      :value: None



   .. py:attribute:: location


   .. py:attribute:: timeout_s


   .. py:method:: segment(request: cellmap_flow.ai_annotate.backends.base.SegmentRequest, model: str) -> cellmap_flow.ai_annotate.backends.base.SegmentResult