Skip to content

components batch_inference_preparer

github-actions[bot] edited this page Nov 9, 2024 · 21 revisions

Batch Inference Preparer

batch_inference_preparer

Overview

Prepare the jsonl file and endpoint for batch inference component.

Version: 0.0.14

View in Studio: https://ml.azure.com/registries/azureml/components/batch_inference_preparer/version/0.0.14

Inputs

Name Description Type Default Optional Enum
input_dataset Input jsonl dataset that contains prompt. For the performance test, this one will be neglected. uri_folder True
model_type Type of model. Can be one of ('aoai', 'oss', 'vision_oss', 'claude') string True
batch_input_pattern The string for the batch input pattern. The input should be the payload format with substitution for the key for the value put in the ###<key>. For example, one can use the following format for a llama text-gen model with a input dataset has prompt for the payload and _batch_request_metadata storing the corresponding ground truth. {"input_data": { "input_string": ["###"], "parameters": { "temperature": 0.6, "max_new_tokens": 100, "do_sample": true } }, "_batch_request_metadata": ###<_batch_request_metadata> } string False
label_column_name The label column name. string True
additional_columns Name(s) of additional column(s) that could be useful to compute metrics, separated by comma (","). string True
is_performance_test If true, the performance test will be run. boolean False
endpoint_url The endpoint name or url. string True
n_samples The number of top samples send to endpoint. integer True

Outputs

Name Description Type
formatted_data Path to the folder where the payload will be stored. mltable
ground_truth_metadata Path to the folder where the ground truth metadata will be stored. uri_folder

Environment

azureml://registries/azureml/environments/evaluation/labels/latest

Clone this wiki locally