ebonite.build.provider.ml_model_multi module

class ebonite.build.provider.ml_model_multi.MLModelMultiProvider(models: List[ebonite.core.objects.core.Model], server: ebonite.runtime.server.base.Server, debug: bool = False)

Bases: ebonite.build.provider.ml_model.MLModelProvider

Provider to put multiple models in one service

Parameters:

• models – List of Model instances
• server – Server instance to build with
• debug – Debug for instance

get_requirements()

Returns union of server, loader and all models requirements

get_sources()

Returns models meta file and custom requirements

get_artifacts() → ebonite.core.objects.artifacts.ArtifactCollection

Returns binaries of models artifacts

get_python_version()

Returns:version of python that produced model

class ebonite.build.provider.ml_model_multi.MultiModelBuildable(model_ids: List[Union[int, ebonite.core.objects.core.Model]], server_type: str, debug: bool = False)

Bases: ebonite.build.provider.utils.BuildableWithServer, ebonite.core.objects.core.WithMetadataRepository

task

property to get task (can be None, whick forces to provide task manually)

models

get_provider() → ebonite.build.provider.ml_model_multi.MLModelMultiProvider

Abstract method to get a provider for this Buildable

type = 'ebonite.build.provider.ml_model_multi.MultiModelBuildable'

class ebonite.build.provider.ml_model_multi.BuildableMultiModelHook

Bases: ebonite.core.analyzer.buildable.BuildableHook, ebonite.core.analyzer.base.CanIsAMustHookMixin

must_process(obj) → bool

Must return True if obj must be processed by this hook. “must” means you sure that no other hook should handle this object, for example this hook is for sklearn objects and obj is exactly that.

Parameters:obj – object to analyze Returns:True or False

process(obj, **kwargs)

Analyzes obj and returns result. Result type is determined by specific Hook class sub-hierarchy

Parameters:

• obj – object to analyze
• kwargs – additional information to be used for analysis

Returns:

analysis result