core.services.context.local_context

local_context

Functions:

Name	Description
create_local_dataset_processing_context	Create a local processing context for running a processing pipeline outside of Picsellia.
create_local_datalake_processing_context	Create a local context for datalake processing pipelines.
create_local_model_processing_context
create_local_training_context	Create a local training context for running a training pipeline outside of Picsellia.

create_local_dataset_processing_context(processing_parameters_cls, organization_name, job_type, input_dataset_version_id, target_version_name=None, output_dataset_version_id=None, target_id=None, model_version_id=None, processing_parameters=None, working_dir=None, api_token=None, host=None, inputs=None, use_id=True, download_annotations=True)

Create a local processing context for running a processing pipeline outside of Picsellia.

This is typically used for development and testing, with full local control over input/output paths and parameter overrides.

Parameters:

Name	Type	Description	Default
processing_parameters_cls	type[TParameters]	A subclass of Parameters used to define typed inputs.	required
api_token	str	API token for authentication with Picsellia.	None
organization_name	str	Name of the Picsellia organization.	required
job_type	ProcessingType	Type of processing job (e.g., PRE_ANNOTATION, DATASET_VERSION_CREATION).	required
input_dataset_version_id	str	ID of the dataset version used as input.	required
target_version_name	str | None	Optional name for the output dataset version.	None
output_dataset_version_id	str | None	Optional ID of an existing dataset version to use as output.	None
target_id	str | None	Optional ID of the processing target.	None
model_version_id	str | None	Optional ID of a model version to include in the context.	None
processing_parameters	dict[str, Any] | None	Raw values to override defaults in the processing parameters.	None
working_dir	str | None	Optional working directory for local file operations.	None
host	str | None	Optional Picsellia API host override.	None
inputs	dict[str, Any] | None	Optional dictionary of additional inputs to include in the context.	None
use_id	bool	Whether to use asset IDs or paths in output annotations.	True
download_annotations	bool	Whether to download annotations for the input dataset version.	True

Returns:

Type	Description
LocalDatasetProcessingContext	LocalDatasetProcessingContext[TParameters]: A fully initialized local processing context.

create_local_datalake_processing_context(processing_parameters_cls, organization_name, job_type, input_datalake_id, output_datalake_id=None, model_version_id=None, target_id=None, inputs=None, offset=0, limit=100, use_id=True, processing_parameters=None, working_dir=None, api_token=None, host=None)

Create a local context for datalake processing pipelines.

Parameters:

Name	Type	Description	Default
processing_parameters_cls	type[TParameters]	Class used to parse processing parameters.	required
api_token	str | None	Your Picsellia API token.	None
organization_name	str	Name of your organization.	required
job_type	ProcessingType	Type of processing job.	required
input_datalake_id	str	ID of the input datalake.	required
output_datalake_id	str | None	Optional ID of the output datalake.	None
model_version_id	str | None	Optional ID of the model version.	None
target_id	str | None	Optional ID of the processing target.	None
inputs	dict[str, Any] | None	Optional dictionary of additional inputs to include in the context.	None
offset	int	Data offset for datalake slicing.	0
limit	int	Max number of samples to fetch.	100
use_id	bool	Whether to use asset ID or path in output annotations.	True
processing_parameters	dict[str, Any] | None	Raw values to override defaults in the processing parameters.	None
working_dir	str | None	Optional working directory.	None
host	str | None	Optional custom API host.	None

Returns:

Type	Description
LocalDatalakeProcessingContext	LocalDatalakeProcessingContext

create_local_model_processing_context(processing_parameters_cls, organization_name, job_type, input_model_version_id, target_id=None, inputs=None, processing_parameters=None, working_dir=None, api_token=None, host=None)

create_local_training_context(hyperparameters_cls, augmentation_parameters_cls, export_parameters_cls, organization_name, experiment_id, hyperparameters=None, augmentation_parameters=None, export_parameters=None, working_dir=None, api_token=None, host=None)

Create a local training context for running a training pipeline outside of Picsellia.

This is typically used for development and debugging, with full local control over hyperparameters, augmentation strategies, and export configuration. Parameters can be pulled from the experiment logs or overridden manually.

Parameters:

Name	Type	Description	Default
hyperparameters_cls	type[HyperParameters]	Class defining the training hyperparameters.	required
augmentation_parameters_cls	type[AugmentationParameters]	Class defining data augmentation parameters.	required
export_parameters_cls	type[ExportParameters]	Class defining model export parameters.	required
api_token	str	API token for authentication with Picsellia.	None
organization_name	str	Name of the Picsellia organization.	required
experiment_id	str	ID of the experiment from which to load parameter logs.	required
hyperparameters	dict[str, Any] | None	Optional overrides for training hyperparameters.	None
augmentation_parameters	dict[str, Any] | None	Optional overrides for augmentation parameters.	None
export_parameters	dict[str, Any] | None	Optional overrides for export parameters.	None
working_dir	str | None	Optional working directory for local file operations.	None
host	str | None	Optional Picsellia API host override.	None

Returns:

Name	Type	Description
LocalTrainingContext	LocalTrainingContext	A fully initialized local training context.