locations

Creates, updates, deletes, gets or lists a locations resource.

Overview

Name	locations
Type	Resource
Id	google.aiplatform.locations

Fields

The following fields are returned by SELECT queries:

get

Successful response

Name	Datatype	Description
name	string	Resource name for the location, which may vary between implementations. For example: "projects/example-project/locations/us-east1"
displayName	string	The friendly name for this location, typically a nearby city name. For example, "Tokyo".
labels	object	Cross-service attributes for the location. For example {"cloud.googleapis.com/region": "us-east1"}
locationId	string	The canonical id for this location. For example: "us-east1".
metadata	object	Service-specific metadata. For example the available capacity at the given location.

list

Successful response

Name	Datatype	Description
name	string	Resource name for the location, which may vary between implementations. For example: "projects/example-project/locations/us-east1"
displayName	string	The friendly name for this location, typically a nearby city name. For example, "Tokyo".
labels	object	Cross-service attributes for the location. For example {"cloud.googleapis.com/region": "us-east1"}
locationId	string	The canonical id for this location. For example: "us-east1".
metadata	object	Service-specific metadata. For example the available capacity at the given location.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get	select	projectsId, locationsId		Gets information about a location.
list	select	projectsId	filter, pageSize, pageToken, extraLocationTypes	Lists information about the supported locations for this service.
evaluate_instances	exec	projectsId, locationsId		Evaluates instances based on a given metric.
evaluate_dataset	exec	projectsId, locationsId		Evaluates a dataset based on a set of given metrics.
generate_instance_rubrics	exec	projectsId, locationsId		Generates rubrics for a given prompt. A rubric represents a single testable criterion for evaluation. One input prompt could have multiple rubrics This RPC allows users to get suggested rubrics based on provided prompt, which can then be reviewed and used for subsequent evaluations.
deploy	exec	projectsId, locationsId		Deploys a model to a new endpoint.
augment_prompt	exec	projectsId, locationsId		Given an input prompt, it returns augmented prompt from vertex rag store to guide LLM towards generating grounded responses.
corroborate_content	exec	projectsId, locationsId		Given an input text, it returns a score that evaluates the factuality of the text. It also extracts and returns claims from the text and provides supporting facts.

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
locationsId	string
projectsId	string
extraLocationTypes	string
filter	string
pageSize	integer (int32)
pageToken	string

SELECT examples

get

Gets information about a location.

SELECT
name,
displayName,
labels,
locationId,
metadata
FROM google.aiplatform.locations
WHERE projectsId = '{{ projectsId }}' -- required
AND locationsId = '{{ locationsId }}' -- required;

list

Lists information about the supported locations for this service.

SELECT
name,
displayName,
labels,
locationId,
metadata
FROM google.aiplatform.locations
WHERE projectsId = '{{ projectsId }}' -- required
AND filter = '{{ filter }}'
AND pageSize = '{{ pageSize }}'
AND pageToken = '{{ pageToken }}'
AND extraLocationTypes = '{{ extraLocationTypes }}';

Lifecycle Methods

evaluate_instances

Evaluates instances based on a given metric.

EXEC google.aiplatform.locations.evaluate_instances 
@projectsId='{{ projectsId }}' --required, 
@locationsId='{{ locationsId }}' --required 
@@json=
'{
"exactMatchInput": "{{ exactMatchInput }}", 
"bleuInput": "{{ bleuInput }}", 
"rougeInput": "{{ rougeInput }}", 
"fluencyInput": "{{ fluencyInput }}", 
"coherenceInput": "{{ coherenceInput }}", 
"safetyInput": "{{ safetyInput }}", 
"groundednessInput": "{{ groundednessInput }}", 
"fulfillmentInput": "{{ fulfillmentInput }}", 
"summarizationQualityInput": "{{ summarizationQualityInput }}", 
"pairwiseSummarizationQualityInput": "{{ pairwiseSummarizationQualityInput }}", 
"summarizationHelpfulnessInput": "{{ summarizationHelpfulnessInput }}", 
"summarizationVerbosityInput": "{{ summarizationVerbosityInput }}", 
"questionAnsweringQualityInput": "{{ questionAnsweringQualityInput }}", 
"pairwiseQuestionAnsweringQualityInput": "{{ pairwiseQuestionAnsweringQualityInput }}", 
"questionAnsweringRelevanceInput": "{{ questionAnsweringRelevanceInput }}", 
"questionAnsweringHelpfulnessInput": "{{ questionAnsweringHelpfulnessInput }}", 
"questionAnsweringCorrectnessInput": "{{ questionAnsweringCorrectnessInput }}", 
"pointwiseMetricInput": "{{ pointwiseMetricInput }}", 
"pairwiseMetricInput": "{{ pairwiseMetricInput }}", 
"toolCallValidInput": "{{ toolCallValidInput }}", 
"toolNameMatchInput": "{{ toolNameMatchInput }}", 
"toolParameterKeyMatchInput": "{{ toolParameterKeyMatchInput }}", 
"toolParameterKvMatchInput": "{{ toolParameterKvMatchInput }}", 
"cometInput": "{{ cometInput }}", 
"metricxInput": "{{ metricxInput }}", 
"trajectoryExactMatchInput": "{{ trajectoryExactMatchInput }}", 
"trajectoryInOrderMatchInput": "{{ trajectoryInOrderMatchInput }}", 
"trajectoryAnyOrderMatchInput": "{{ trajectoryAnyOrderMatchInput }}", 
"trajectoryPrecisionInput": "{{ trajectoryPrecisionInput }}", 
"trajectoryRecallInput": "{{ trajectoryRecallInput }}", 
"trajectorySingleToolUseInput": "{{ trajectorySingleToolUseInput }}", 
"rubricBasedInstructionFollowingInput": "{{ rubricBasedInstructionFollowingInput }}", 
"metrics": "{{ metrics }}", 
"instance": "{{ instance }}", 
"autoraterConfig": "{{ autoraterConfig }}"
}';

evaluate_dataset

Evaluates a dataset based on a set of given metrics.

EXEC google.aiplatform.locations.evaluate_dataset 
@projectsId='{{ projectsId }}' --required, 
@locationsId='{{ locationsId }}' --required 
@@json=
'{
"dataset": "{{ dataset }}", 
"metrics": "{{ metrics }}", 
"outputConfig": "{{ outputConfig }}", 
"autoraterConfig": "{{ autoraterConfig }}"
}';

generate_instance_rubrics

Generates rubrics for a given prompt. A rubric represents a single testable criterion for evaluation. One input prompt could have multiple rubrics This RPC allows users to get suggested rubrics based on provided prompt, which can then be reviewed and used for subsequent evaluations.

EXEC google.aiplatform.locations.generate_instance_rubrics 
@projectsId='{{ projectsId }}' --required, 
@locationsId='{{ locationsId }}' --required 
@@json=
'{
"contents": "{{ contents }}", 
"predefinedRubricGenerationSpec": "{{ predefinedRubricGenerationSpec }}", 
"rubricGenerationSpec": "{{ rubricGenerationSpec }}"
}';

deploy

Deploys a model to a new endpoint.

EXEC google.aiplatform.locations.deploy 
@projectsId='{{ projectsId }}' --required, 
@locationsId='{{ locationsId }}' --required 
@@json=
'{
"publisherModelName": "{{ publisherModelName }}", 
"huggingFaceModelId": "{{ huggingFaceModelId }}", 
"modelConfig": "{{ modelConfig }}", 
"endpointConfig": "{{ endpointConfig }}", 
"deployConfig": "{{ deployConfig }}"
}';

augment_prompt

Given an input prompt, it returns augmented prompt from vertex rag store to guide LLM towards generating grounded responses.

EXEC google.aiplatform.locations.augment_prompt 
@projectsId='{{ projectsId }}' --required, 
@locationsId='{{ locationsId }}' --required 
@@json=
'{
"vertexRagStore": "{{ vertexRagStore }}", 
"contents": "{{ contents }}", 
"model": "{{ model }}"
}';

corroborate_content

Given an input text, it returns a score that evaluates the factuality of the text. It also extracts and returns claims from the text and provides supporting facts.

EXEC google.aiplatform.locations.corroborate_content 
@projectsId='{{ projectsId }}' --required, 
@locationsId='{{ locationsId }}' --required 
@@json=
'{
"content": "{{ content }}", 
"facts": "{{ facts }}", 
"parameters": "{{ parameters }}"
}';