evaluation_results

Creates, updates, deletes, gets or lists an evaluation_results resource.

Overview

Name	evaluation_results
Type	Resource
Id	azure.ai_evaluation.evaluation_results

Fields

The following fields are returned by SELECT queries:

get_credentials

Name	Datatype	Description
blobReference	object	Credential info to access the storage account. Required.

get_version

Name	Datatype	Description
id	string	Asset ID, a unique identifier for the asset.
name	string	The name of the resource. Required.
blobUri	string	Blob URI.
description	string	The asset description text.
metrics	object	Aggregated metrics.
resultType	string	Type of Evaluation result. Known values are: "Benchmark", "Evaluation", "Redteam", and "Simulation". (Benchmark, Evaluation, Redteam, Simulation)
tags	object	Tag dictionary. Tags can be added, removed, and updated.
version	string	The version of the resource. Required.

list_versions

Name	Datatype	Description
id	string	Asset ID, a unique identifier for the asset.
name	string	The name of the resource. Required.
blobUri	string	Blob URI.
description	string	The asset description text.
metrics	object	Aggregated metrics.
resultType	string	Type of Evaluation result. Known values are: "Benchmark", "Evaluation", "Redteam", and "Simulation". (Benchmark, Evaluation, Redteam, Simulation)
tags	object	Tag dictionary. Tags can be added, removed, and updated.
version	string	The version of the resource. Required.

list_latest

Name	Datatype	Description
id	string	Asset ID, a unique identifier for the asset.
name	string	The name of the resource. Required.
blobUri	string	Blob URI.
description	string	The asset description text.
metrics	object	Aggregated metrics.
resultType	string	Type of Evaluation result. Known values are: "Benchmark", "Evaluation", "Redteam", and "Simulation". (Benchmark, Evaluation, Redteam, Simulation)
tags	object	Tag dictionary. Tags can be added, removed, and updated.
version	string	The version of the resource. Required.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get_credentials	select	name, version, endpoint		Enable downloading json.
get_version	select	name, version, endpoint		Get the specific version of the EvaluationResult. The service returns 404 Not Found error if the EvaluationResult does not exist.
list_versions	select	name, endpoint	top, skip, tags, listViewType	List all versions of the given EvaluationResult.
list_latest	select	endpoint	top, skip, tags, listViewType	List the latest version of each EvaluationResult.
delete_version	exec	name, version, endpoint		Delete the specific version of the EvaluationResult. The service returns 204 No Content if the EvaluationResult was deleted successfully or if the EvaluationResult does not exist.
create_or_update_version	exec	name, version, endpoint		Create a new or update an existing EvaluationResult with the given version id.
start_pending_upload	exec	name, version, endpoint, pendingUploadType		Create or start a pending upload of a evaluation results for a specific version.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
endpoint	string	The service endpoint host (no scheme), e.g. myaccount.table.cosmos.azure.com:443 - value of the client endpoint parameter. (default: )
name	string	The name of the resource. Required.
version	string	The specific version id of the EvaluationResult to operate on. Required.
listViewType	string	[ListViewType.ActiveOnly, ListViewType.ArchivedOnly, ListViewType.All] View type for including/excluding (for example) archived entities. Known values are: "ActiveOnly", "ArchivedOnly", and "All". Default value is None.
skip	string	Continuation token for pagination. Default value is None.
tags	string	Comma-separated list of tag names (and optionally values). Example: tag1,tag2=value2. Default value is None.
top	integer	Top count of results, top count cannot be greater than the page size. If topCount > page size, results with be default page size count will be returned. Default value is None.

SELECT examples

get_credentials

Enable downloading json.

SELECT
blobReference
FROM azure.ai_evaluation.evaluation_results
WHERE name = '{{ name }}' -- required
AND version = '{{ version }}' -- required
AND endpoint = '{{ endpoint }}' -- required
;

get_version

Get the specific version of the EvaluationResult. The service returns 404 Not Found error if the EvaluationResult does not exist.

SELECT
id,
name,
blobUri,
description,
metrics,
resultType,
tags,
version
FROM azure.ai_evaluation.evaluation_results
WHERE name = '{{ name }}' -- required
AND version = '{{ version }}' -- required
AND endpoint = '{{ endpoint }}' -- required
;

list_versions

List all versions of the given EvaluationResult.

SELECT
id,
name,
blobUri,
description,
metrics,
resultType,
tags,
version
FROM azure.ai_evaluation.evaluation_results
WHERE name = '{{ name }}' -- required
AND endpoint = '{{ endpoint }}' -- required
AND top = '{{ top }}'
AND skip = '{{ skip }}'
AND tags = '{{ tags }}'
AND listViewType = '{{ listViewType }}'
;

list_latest

List the latest version of each EvaluationResult.

SELECT
id,
name,
blobUri,
description,
metrics,
resultType,
tags,
version
FROM azure.ai_evaluation.evaluation_results
WHERE endpoint = '{{ endpoint }}' -- required
AND top = '{{ top }}'
AND skip = '{{ skip }}'
AND tags = '{{ tags }}'
AND listViewType = '{{ listViewType }}'
;

Lifecycle Methods

delete_version

Delete the specific version of the EvaluationResult. The service returns 204 No Content if the EvaluationResult was deleted successfully or if the EvaluationResult does not exist.

EXEC azure.ai_evaluation.evaluation_results.delete_version 
@name='{{ name }}' --required, 
@version='{{ version }}' --required, 
@endpoint='{{ endpoint }}' --required
;

create_or_update_version

Create a new or update an existing EvaluationResult with the given version id.

EXEC azure.ai_evaluation.evaluation_results.create_or_update_version 
@name='{{ name }}' --required, 
@version='{{ version }}' --required, 
@endpoint='{{ endpoint }}' --required 
@@json=
'{
"resultType": "{{ resultType }}", 
"metrics": "{{ metrics }}", 
"blobUri": "{{ blobUri }}", 
"description": "{{ description }}", 
"tags": "{{ tags }}"
}'
;

start_pending_upload

Create or start a pending upload of a evaluation results for a specific version.

EXEC azure.ai_evaluation.evaluation_results.start_pending_upload 
@name='{{ name }}' --required, 
@version='{{ version }}' --required, 
@endpoint='{{ endpoint }}' --required 
@@json=
'{
"pendingUploadId": "{{ pendingUploadId }}", 
"connectionName": "{{ connectionName }}", 
"pendingUploadType": "{{ pendingUploadType }}"
}'
;