components batch_benchmark_score - Azure/azureml-assets GitHub Wiki
Version: 0.0.6
View in Studio: https://ml.azure.com/registries/azureml/components/batch_benchmark_score/version/0.0.6
Name | Description | Type | Default | Optional | Enum |
---|---|---|---|---|---|
data_input_table | The data to be split and scored in parallel. | mltable | False | ||
model_type | Type of model. Can be one of ('aoai', 'oss', 'vision_oss', 'claude') | string | True | ||
online_endpoint_url | Online endpoint url. | string | False | ||
deployment_name | Deployment name for the model. Can be optional for OAI models. | string | True | ||
connections_name | Connections name for the endpoint. | string | False | ||
additional_properties | A stringified json expressing additional properties to be added to each request body at the top level. | string | True | ||
additional_headers | A stringified json expressing additional headers to be added to each request. | string | True | ||
mini_batch_size | The mini batch size for parallel run. | string | True | ||
user_agent_segment | A user-provided segment to be included in the User-Agent header for all requests sent by the component. The overall user agent format is "BatchScoreComponent:/Workload:<batch_pool>:<quota_audience>:<user_agent_segment>/Run:<workspace_name>:<run_id>" | string | True | ||
ensure_ascii | If ensure_ascii is true, the output is guaranteed to have all incoming non-ASCII characters escaped. If ensure_ascii is false, these characters will be output as-is. More defailted information can be found at https://docs.python.org/3/library/json.html | boolean | False | False | |
max_retry_time_interval | The maximum time (in seconds) spent retrying a payload. If unspecified, payloads are retried unlimited times. | integer | True | ||
initial_worker_count | integer | 5 | False | ||
max_worker_count | Overrides initial_worker_count if necessary | integer | 200 | False | |
debug_mode | Enable debug mode will print all the debug logs in the score step. | boolean | False | False | |
deployment_metadata | The deployment metadata directory that contains deployment details. | uri_file | True |
Name | Description | Type |
---|---|---|
job_out_path | uri_file | |
mini_batch_results_out_directory | uri_folder | |
metrics_out_directory | uri_folder |