components gsq_annotation_compute_histogram

Annotation - Compute Histogram

gsq_annotation_compute_histogram

Overview

Compute annotation histogram given a deployment's model data input.

Version: 0.4.37

View in Studio: https://ml.azure.com/registries/azureml/components/gsq_annotation_compute_histogram/version/0.4.37

Inputs

Name	Description	Type	Default	Optional	Enum
production_dataset		mltable
metric_names	a comma-separated list of metric names to compute	string		False
model_deployment_name	model name, e.g., name of the deployment for Azure OpenAI	string		False
workspace_connection_arm_id	path to the workspace connection	string		False
prompt_column_name		string	prompt	True
completion_column_name		string	completion	True
ground_truth_column_name		string	ground_truth	True
context_column_name		string	context	True
groundedness_rating_threshold		integer	3	True
similarity_rating_threshold		integer	3	True
relevance_rating_threshold		integer	3	True
fluency_rating_threshold		integer	3	True
coherence_rating_threshold		integer	3	True
sample_rate	sample rate for the input dataset, should be greater than 0 and at most 1	number		True

Outputs

Name	Description	Type
histogram		mltable
samples_index		mltable
groundedness_violations		mltable
fluency_violations		mltable
coherence_violations		mltable
similarity_violations		mltable
relevance_violations		mltable
evaluation	evaluation results	mltable