-
Notifications
You must be signed in to change notification settings - Fork 126
components rai_text_insights
github-actions[bot] edited this page Oct 22, 2023
·
20 revisions
Description:
Version: 0.0.10
Preview
View in Studio: https://ml.azure.com/registries/azureml/components/rai_text_insights/version/0.0.10
Name | Description | Type | Default | Optional | Enum |
---|---|---|---|---|---|
task_type | The type of task to perform | string | ['text_classification', 'multilabel_text_classification', 'question_answering'] | ||
model_input | The model name to be used for computing insights | mlflow_model | False | ||
model_info | The model name to be used for computing insights | string | False | ||
test_dataset | The test dataset to be used for computing insights | mltable | |||
target_column_name | The target column name | string | |||
text_column_name | Optional text column name, required if metadata present | string | True | ||
maximum_rows_for_test_dataset | The maximum number of rows to use from the test dataset | integer | 5000 | ||
classes | The list of class names for the target column | string | [] | ||
categorical_metadata_features | The list of categorical metadata feature names | string | [] | ||
dropped_metadata_features | The list of dropped metadata feature names | string | [] | ||
enable_explanation | Whether to enable computation of explanations | boolean | True | ||
enable_error_analysis | Whether to enable computation of error analysis | boolean | True | ||
use_model_dependency | Whether to install the MLFlow model's dependencies in the RAI environment | boolean | False | ||
use_conda | Whether to use conda or pip to install the MLFlow model's dependencies in the RAI environment | boolean | False |
Name | Description | Type |
---|---|---|
dashboard | Path to which RAITextInsights is serialized to for connecting to compute instance | path |
ux_json | Json file to which UX is serialized to for viewing in static AzureML Studio UI | path |
azureml://registries/azureml/environments/responsibleai-text-ubuntu20.04-py38-cpu/versions/30