google-native logo
Google Cloud Native v0.28.0, Feb 2 23

google-native.dialogflow/v2.getEvaluation

Gets an evaluation of conversation model.

Using getEvaluation

Two invocation forms are available. The direct form accepts plain arguments and either blocks until the result value is available, or returns a Promise-wrapped result. The output form accepts Input-wrapped arguments and returns an Output-wrapped result.

function getEvaluation(args: GetEvaluationArgs, opts?: InvokeOptions): Promise<GetEvaluationResult>
function getEvaluationOutput(args: GetEvaluationOutputArgs, opts?: InvokeOptions): Output<GetEvaluationResult>
def get_evaluation(conversation_model_id: Optional[str] = None,
                   evaluation_id: Optional[str] = None,
                   location: Optional[str] = None,
                   project: Optional[str] = None,
                   opts: Optional[InvokeOptions] = None) -> GetEvaluationResult
def get_evaluation_output(conversation_model_id: Optional[pulumi.Input[str]] = None,
                   evaluation_id: Optional[pulumi.Input[str]] = None,
                   location: Optional[pulumi.Input[str]] = None,
                   project: Optional[pulumi.Input[str]] = None,
                   opts: Optional[InvokeOptions] = None) -> Output[GetEvaluationResult]
func LookupEvaluation(ctx *Context, args *LookupEvaluationArgs, opts ...InvokeOption) (*LookupEvaluationResult, error)
func LookupEvaluationOutput(ctx *Context, args *LookupEvaluationOutputArgs, opts ...InvokeOption) LookupEvaluationResultOutput

> Note: This function is named LookupEvaluation in the Go SDK.

public static class GetEvaluation 
{
    public static Task<GetEvaluationResult> InvokeAsync(GetEvaluationArgs args, InvokeOptions? opts = null)
    public static Output<GetEvaluationResult> Invoke(GetEvaluationInvokeArgs args, InvokeOptions? opts = null)
}
public static CompletableFuture<GetEvaluationResult> getEvaluation(GetEvaluationArgs args, InvokeOptions options)
// Output-based functions aren't available in Java yet
fn::invoke:
  function: google-native:dialogflow/v2:getEvaluation
  arguments:
    # arguments dictionary

The following arguments are supported:

getEvaluation Result

The following output properties are available:

CreateTime string

Creation time of this model.

DisplayName string

Optional. The display name of the model evaluation. At most 64 bytes long.

EvaluationConfig Pulumi.GoogleNative.Dialogflow.V2.Outputs.GoogleCloudDialogflowV2EvaluationConfigResponse

Optional. The configuration of the evaluation task.

Name string

The resource name of the evaluation. Format: projects//conversationModels//evaluations/

RawHumanEvalTemplateCsv string

Human eval template in csv format. It tooks real-world conversations provided through input dataset, generates example suggestions for customer to verify quality of the model. For Smart Reply, the generated csv file contains columns of Context, (Suggestions,Q1,Q2)*3, Actual reply. Context contains at most 10 latest messages in the conversation prior to the current suggestion. Q1: "Would you send it as the next message of agent?" Evaluated based on whether the suggest is appropriate to be sent by agent in current context. Q2: "Does the suggestion move the conversation closer to resolution?" Evaluated based on whether the suggestion provide solutions, or answers customer's question or collect information from customer to resolve the customer's issue. Actual reply column contains the actual agent reply sent in the context.

SmartReplyMetrics Pulumi.GoogleNative.Dialogflow.V2.Outputs.GoogleCloudDialogflowV2SmartReplyMetricsResponse

Only available when model is for smart reply.

CreateTime string

Creation time of this model.

DisplayName string

Optional. The display name of the model evaluation. At most 64 bytes long.

EvaluationConfig GoogleCloudDialogflowV2EvaluationConfigResponse

Optional. The configuration of the evaluation task.

Name string

The resource name of the evaluation. Format: projects//conversationModels//evaluations/

RawHumanEvalTemplateCsv string

Human eval template in csv format. It tooks real-world conversations provided through input dataset, generates example suggestions for customer to verify quality of the model. For Smart Reply, the generated csv file contains columns of Context, (Suggestions,Q1,Q2)*3, Actual reply. Context contains at most 10 latest messages in the conversation prior to the current suggestion. Q1: "Would you send it as the next message of agent?" Evaluated based on whether the suggest is appropriate to be sent by agent in current context. Q2: "Does the suggestion move the conversation closer to resolution?" Evaluated based on whether the suggestion provide solutions, or answers customer's question or collect information from customer to resolve the customer's issue. Actual reply column contains the actual agent reply sent in the context.

SmartReplyMetrics GoogleCloudDialogflowV2SmartReplyMetricsResponse

Only available when model is for smart reply.

createTime String

Creation time of this model.

displayName String

Optional. The display name of the model evaluation. At most 64 bytes long.

evaluationConfig GoogleCloudDialogflowV2EvaluationConfigResponse

Optional. The configuration of the evaluation task.

name String

The resource name of the evaluation. Format: projects//conversationModels//evaluations/

rawHumanEvalTemplateCsv String

Human eval template in csv format. It tooks real-world conversations provided through input dataset, generates example suggestions for customer to verify quality of the model. For Smart Reply, the generated csv file contains columns of Context, (Suggestions,Q1,Q2)*3, Actual reply. Context contains at most 10 latest messages in the conversation prior to the current suggestion. Q1: "Would you send it as the next message of agent?" Evaluated based on whether the suggest is appropriate to be sent by agent in current context. Q2: "Does the suggestion move the conversation closer to resolution?" Evaluated based on whether the suggestion provide solutions, or answers customer's question or collect information from customer to resolve the customer's issue. Actual reply column contains the actual agent reply sent in the context.

smartReplyMetrics GoogleCloudDialogflowV2SmartReplyMetricsResponse

Only available when model is for smart reply.

createTime string

Creation time of this model.

displayName string

Optional. The display name of the model evaluation. At most 64 bytes long.

evaluationConfig GoogleCloudDialogflowV2EvaluationConfigResponse

Optional. The configuration of the evaluation task.

name string

The resource name of the evaluation. Format: projects//conversationModels//evaluations/

rawHumanEvalTemplateCsv string

Human eval template in csv format. It tooks real-world conversations provided through input dataset, generates example suggestions for customer to verify quality of the model. For Smart Reply, the generated csv file contains columns of Context, (Suggestions,Q1,Q2)*3, Actual reply. Context contains at most 10 latest messages in the conversation prior to the current suggestion. Q1: "Would you send it as the next message of agent?" Evaluated based on whether the suggest is appropriate to be sent by agent in current context. Q2: "Does the suggestion move the conversation closer to resolution?" Evaluated based on whether the suggestion provide solutions, or answers customer's question or collect information from customer to resolve the customer's issue. Actual reply column contains the actual agent reply sent in the context.

smartReplyMetrics GoogleCloudDialogflowV2SmartReplyMetricsResponse

Only available when model is for smart reply.

create_time str

Creation time of this model.

display_name str

Optional. The display name of the model evaluation. At most 64 bytes long.

evaluation_config GoogleCloudDialogflowV2EvaluationConfigResponse

Optional. The configuration of the evaluation task.

name str

The resource name of the evaluation. Format: projects//conversationModels//evaluations/

raw_human_eval_template_csv str

Human eval template in csv format. It tooks real-world conversations provided through input dataset, generates example suggestions for customer to verify quality of the model. For Smart Reply, the generated csv file contains columns of Context, (Suggestions,Q1,Q2)*3, Actual reply. Context contains at most 10 latest messages in the conversation prior to the current suggestion. Q1: "Would you send it as the next message of agent?" Evaluated based on whether the suggest is appropriate to be sent by agent in current context. Q2: "Does the suggestion move the conversation closer to resolution?" Evaluated based on whether the suggestion provide solutions, or answers customer's question or collect information from customer to resolve the customer's issue. Actual reply column contains the actual agent reply sent in the context.

smart_reply_metrics GoogleCloudDialogflowV2SmartReplyMetricsResponse

Only available when model is for smart reply.

createTime String

Creation time of this model.

displayName String

Optional. The display name of the model evaluation. At most 64 bytes long.

evaluationConfig Property Map

Optional. The configuration of the evaluation task.

name String

The resource name of the evaluation. Format: projects//conversationModels//evaluations/

rawHumanEvalTemplateCsv String

Human eval template in csv format. It tooks real-world conversations provided through input dataset, generates example suggestions for customer to verify quality of the model. For Smart Reply, the generated csv file contains columns of Context, (Suggestions,Q1,Q2)*3, Actual reply. Context contains at most 10 latest messages in the conversation prior to the current suggestion. Q1: "Would you send it as the next message of agent?" Evaluated based on whether the suggest is appropriate to be sent by agent in current context. Q2: "Does the suggestion move the conversation closer to resolution?" Evaluated based on whether the suggestion provide solutions, or answers customer's question or collect information from customer to resolve the customer's issue. Actual reply column contains the actual agent reply sent in the context.

smartReplyMetrics Property Map

Only available when model is for smart reply.

Supporting Types

GoogleCloudDialogflowV2EvaluationConfigResponse

datasets List<Property Map>

Datasets used for evaluation.

smartComposeConfig Property Map

Configuration for smart compose model evalution.

smartReplyConfig Property Map

Configuration for smart reply model evalution.

GoogleCloudDialogflowV2EvaluationConfigSmartComposeConfigResponse

AllowlistDocument string

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart compose model.

MaxResultCount int

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

AllowlistDocument string

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart compose model.

MaxResultCount int

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

allowlistDocument String

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart compose model.

maxResultCount Integer

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

allowlistDocument string

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart compose model.

maxResultCount number

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

allowlist_document str

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart compose model.

max_result_count int

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

allowlistDocument String

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart compose model.

maxResultCount Number

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

GoogleCloudDialogflowV2EvaluationConfigSmartReplyConfigResponse

AllowlistDocument string

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart reply model.

MaxResultCount int

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

AllowlistDocument string

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart reply model.

MaxResultCount int

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

allowlistDocument String

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart reply model.

maxResultCount Integer

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

allowlistDocument string

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart reply model.

maxResultCount number

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

allowlist_document str

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart reply model.

max_result_count int

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

allowlistDocument String

The allowlist document resource name. Format: projects//knowledgeBases//documents/. Only used for smart reply model.

maxResultCount Number

The model to be evaluated can return multiple results with confidence score on each query. These results will be sorted by the descending order of the scores and we only keep the first max_result_count results as the final results to evaluate.

GoogleCloudDialogflowV2InputDatasetResponse

Dataset string

ConversationDataset resource name. Format: projects//locations//conversationDatasets/

Dataset string

ConversationDataset resource name. Format: projects//locations//conversationDatasets/

dataset String

ConversationDataset resource name. Format: projects//locations//conversationDatasets/

dataset string

ConversationDataset resource name. Format: projects//locations//conversationDatasets/

dataset str

ConversationDataset resource name. Format: projects//locations//conversationDatasets/

dataset String

ConversationDataset resource name. Format: projects//locations//conversationDatasets/

GoogleCloudDialogflowV2SmartReplyMetricsResponse

AllowlistCoverage double

Percentage of target participant messages in the evaluation dataset for which similar messages have appeared at least once in the allowlist. Should be [0, 1].

ConversationCount string

Total number of conversations used to generate this metric.

TopNMetrics List<Pulumi.GoogleNative.Dialogflow.V2.Inputs.GoogleCloudDialogflowV2SmartReplyMetricsTopNMetricsResponse>

Metrics of top n smart replies, sorted by TopNMetric.n.

AllowlistCoverage float64

Percentage of target participant messages in the evaluation dataset for which similar messages have appeared at least once in the allowlist. Should be [0, 1].

ConversationCount string

Total number of conversations used to generate this metric.

TopNMetrics []GoogleCloudDialogflowV2SmartReplyMetricsTopNMetricsResponse

Metrics of top n smart replies, sorted by TopNMetric.n.

allowlistCoverage Double

Percentage of target participant messages in the evaluation dataset for which similar messages have appeared at least once in the allowlist. Should be [0, 1].

conversationCount String

Total number of conversations used to generate this metric.

topNMetrics List<GoogleCloudDialogflowV2SmartReplyMetricsTopNMetricsResponse>

Metrics of top n smart replies, sorted by TopNMetric.n.

allowlistCoverage number

Percentage of target participant messages in the evaluation dataset for which similar messages have appeared at least once in the allowlist. Should be [0, 1].

conversationCount string

Total number of conversations used to generate this metric.

topNMetrics GoogleCloudDialogflowV2SmartReplyMetricsTopNMetricsResponse[]

Metrics of top n smart replies, sorted by TopNMetric.n.

allowlist_coverage float

Percentage of target participant messages in the evaluation dataset for which similar messages have appeared at least once in the allowlist. Should be [0, 1].

conversation_count str

Total number of conversations used to generate this metric.

top_n_metrics Sequence[GoogleCloudDialogflowV2SmartReplyMetricsTopNMetricsResponse]

Metrics of top n smart replies, sorted by TopNMetric.n.

allowlistCoverage Number

Percentage of target participant messages in the evaluation dataset for which similar messages have appeared at least once in the allowlist. Should be [0, 1].

conversationCount String

Total number of conversations used to generate this metric.

topNMetrics List<Property Map>

Metrics of top n smart replies, sorted by TopNMetric.n.

GoogleCloudDialogflowV2SmartReplyMetricsTopNMetricsResponse

N int

Number of retrieved smart replies. For example, when n is 3, this evaluation contains metrics for when Dialogflow retrieves 3 smart replies with the model.

Recall double

Defined as number of queries whose top n smart replies have at least one similar (token match similarity above the defined threshold) reply as the real reply divided by number of queries with at least one smart reply. Value ranges from 0.0 to 1.0 inclusive.

N int

Number of retrieved smart replies. For example, when n is 3, this evaluation contains metrics for when Dialogflow retrieves 3 smart replies with the model.

Recall float64

Defined as number of queries whose top n smart replies have at least one similar (token match similarity above the defined threshold) reply as the real reply divided by number of queries with at least one smart reply. Value ranges from 0.0 to 1.0 inclusive.

n Integer

Number of retrieved smart replies. For example, when n is 3, this evaluation contains metrics for when Dialogflow retrieves 3 smart replies with the model.

recall Double

Defined as number of queries whose top n smart replies have at least one similar (token match similarity above the defined threshold) reply as the real reply divided by number of queries with at least one smart reply. Value ranges from 0.0 to 1.0 inclusive.

n number

Number of retrieved smart replies. For example, when n is 3, this evaluation contains metrics for when Dialogflow retrieves 3 smart replies with the model.

recall number

Defined as number of queries whose top n smart replies have at least one similar (token match similarity above the defined threshold) reply as the real reply divided by number of queries with at least one smart reply. Value ranges from 0.0 to 1.0 inclusive.

n int

Number of retrieved smart replies. For example, when n is 3, this evaluation contains metrics for when Dialogflow retrieves 3 smart replies with the model.

recall float

Defined as number of queries whose top n smart replies have at least one similar (token match similarity above the defined threshold) reply as the real reply divided by number of queries with at least one smart reply. Value ranges from 0.0 to 1.0 inclusive.

n Number

Number of retrieved smart replies. For example, when n is 3, this evaluation contains metrics for when Dialogflow retrieves 3 smart replies with the model.

recall Number

Defined as number of queries whose top n smart replies have at least one similar (token match similarity above the defined threshold) reply as the real reply divided by number of queries with at least one smart reply. Value ranges from 0.0 to 1.0 inclusive.

Package Details

Repository
Google Cloud Native pulumi/pulumi-google-native
License
Apache-2.0