REST Resource: projects.conversationProfiles

Resource: ConversationProfile

Defines the services to connect to incoming Dialogflow conversations.

JSON representation
{
  "name": string,
  "displayName": string,
  "createTime": string,
  "updateTime": string,
  "automatedAgentConfig": {
    object (AutomatedAgentConfig)
  },
  "humanAgentAssistantConfig": {
    object (HumanAgentAssistantConfig)
  },
  "humanAgentHandoffConfig": {
    object (HumanAgentHandoffConfig)
  },
  "notificationConfig": {
    object (NotificationConfig)
  },
  "loggingConfig": {
    object (LoggingConfig)
  },
  "newMessageEventNotificationConfig": {
    object (NotificationConfig)
  },
  "sttConfig": {
    object (SpeechToTextConfig)
  },
  "languageCode": string
}
Fields
name

string

The unique identifier of this conversation profile. Format: projects/<Project ID>/locations/<Location ID>/conversationProfiles/<Conversation Profile ID>.

displayName

string

Required. Human readable name for this profile. Max length 1024 bytes.

createTime

string (Timestamp format)

Output only. Create time of the conversation profile.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

updateTime

string (Timestamp format)

Output only. Update time of the conversation profile.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

automatedAgentConfig

object (AutomatedAgentConfig)

Configuration for an automated agent to use with this profile.

humanAgentAssistantConfig

object (HumanAgentAssistantConfig)

Configuration for agent assistance to use with this profile.

humanAgentHandoffConfig

object (HumanAgentHandoffConfig)

Configuration for connecting to a live agent.

Currently, this feature is not general available, please contact Google to get access.

notificationConfig

object (NotificationConfig)

Configuration for publishing conversation lifecycle events.

loggingConfig

object (LoggingConfig)

Configuration for logging conversation lifecycle events.

newMessageEventNotificationConfig

object (NotificationConfig)

Configuration for publishing new message events. Event will be sent in format of ConversationEvent

sttConfig

object (SpeechToTextConfig)

Settings for speech transcription.

languageCode

string

Language code for the conversation profile. If not specified, the language is en-US. Language at ConversationProfile should be set for all non en-us languages.

AutomatedAgentConfig

Defines the Automated Agent to connect to a conversation.

JSON representation
{
  "agent": string
}
Fields
agent

string

Required. ID of the Dialogflow agent environment to use.

This project needs to either be the same project as the conversation or you need to grant service-<Conversation Project Number>@gcp-sa-dialogflow.iam.gserviceaccount.com the Dialogflow API Service Agent role in this project.

  • For ES agents, use format: projects/<Project ID>/locations/<Location ID>/agent/environments/<Environment ID or '-'>. If environment is not specified, the default draft environment is used. Refer to DetectIntentRequest for more details.

  • For CX agents, use format projects/<Project ID>/locations/<Location ID>/agents/<Agent ID>/environments/<Environment ID or '-'>. If environment is not specified, the default draft environment is used.

HumanAgentAssistantConfig

Defines the Human Agent Assistant to connect to a conversation.

JSON representation
{
  "notificationConfig": {
    object (NotificationConfig)
  },
  "humanAgentSuggestionConfig": {
    object (SuggestionConfig)
  },
  "endUserSuggestionConfig": {
    object (SuggestionConfig)
  },
  "messageAnalysisConfig": {
    object (MessageAnalysisConfig)
  }
}
Fields
notificationConfig

object (NotificationConfig)

Pub/Sub topic on which to publish new agent assistant events.

humanAgentSuggestionConfig

object (SuggestionConfig)

Configuration for agent assistance of human agent participant.

endUserSuggestionConfig

object (SuggestionConfig)

Configuration for agent assistance of end user participant.

Currently, this feature is not general available, please contact Google to get access.

messageAnalysisConfig

object (MessageAnalysisConfig)

Configuration for message analysis.

NotificationConfig

Defines notification behavior.

JSON representation
{
  "topic": string,
  "messageFormat": enum (MessageFormat)
}
Fields
topic

string

Name of the Pub/Sub topic to publish conversation events like CONVERSATION_STARTED as serialized ConversationEvent protos.

Notification works for phone calls, if this topic either is in the same project as the conversation or you grant service-<Conversation Project Number>@gcp-sa-dialogflow.iam.gserviceaccount.com the Dialogflow Service Agent role in the topic project.

Format: projects/<Project ID>/locations/<Location ID>/topics/<Topic ID>.

messageFormat

enum (MessageFormat)

Format of message.

MessageFormat

Format of cloud pub/sub message.

Enums
MESSAGE_FORMAT_UNSPECIFIED If it is unspecified, PROTO will be used.
PROTO Pubsub message will be serialized proto.
JSON Pubsub message will be json.

SuggestionConfig

Detail human agent assistant config.

JSON representation
{
  "featureConfigs": [
    {
      object (SuggestionFeatureConfig)
    }
  ],
  "groupSuggestionResponses": boolean
}
Fields
featureConfigs[]

object (SuggestionFeatureConfig)

Configuration of different suggestion features. One feature can have only one config.

groupSuggestionResponses

boolean

If groupSuggestionResponses is false, and there are multiple featureConfigs in event based suggestion or StreamingAnalyzeContent, we will try to deliver suggestions to customers as soon as we get new suggestion. Different type of suggestions based on the same context will be in separate Pub/Sub event or StreamingAnalyzeContentResponse.

If groupSuggestionResponses set to true. All the suggestions to the same participant based on the same context will be grouped into a single Pub/Sub event or StreamingAnalyzeContentResponse.

SuggestionFeatureConfig

Config for suggestion features.

JSON representation
{
  "suggestionFeature": {
    object (SuggestionFeature)
  },
  "enableEventBasedSuggestion": boolean,
  "suggestionTriggerSettings": {
    object (SuggestionTriggerSettings)
  },
  "queryConfig": {
    object (SuggestionQueryConfig)
  },
  "conversationModelConfig": {
    object (ConversationModelConfig)
  }
}
Fields
suggestionFeature

object (SuggestionFeature)

The suggestion feature.

enableEventBasedSuggestion

boolean

Automatically iterates all participants and tries to compile suggestions.

Supported features: ARTICLE_SUGGESTION, FAQ, DIALOGFLOW_ASSIST.

suggestionTriggerSettings

object (SuggestionTriggerSettings)

Settings of suggestion trigger.

Currently, only ARTICLE_SUGGESTION, FAQ, and DIALOGFLOW_ASSIST will use this field.

queryConfig

object (SuggestionQueryConfig)

Configs of query.

conversationModelConfig

object (ConversationModelConfig)

Configs of custom conversation model.

SuggestionFeature

The type of Human Agent Assistant API suggestion to perform, and the maximum number of results to return for that type. Multiple Feature objects can be specified in the features list.

JSON representation
{
  "type": enum (Type)
}
Fields
type

enum (Type)

Type of Human Agent Assistant API feature to request.

Type

Defines the type of Human Agent Assistant feature.

Enums
TYPE_UNSPECIFIED Unspecified feature type.
ARTICLE_SUGGESTION Run article suggestion model.
FAQ Run FAQ model.
SMART_REPLY Run smart reply model.

SuggestionTriggerSettings

Settings of suggestion trigger.

JSON representation
{
  "noSmallTalk": boolean,
  "onlyEndUser": boolean
}
Fields
noSmallTalk

boolean

Do not trigger if last utterance is small talk.

onlyEndUser

boolean

Only trigger suggestion if participant role of last utterance is END_USER.

SuggestionQueryConfig

Config for suggestion query.

JSON representation
{
  "maxResults": integer,
  "confidenceThreshold": number,
  "contextFilterSettings": {
    object (ContextFilterSettings)
  },

  // Union field query_source can be only one of the following:
  "knowledgeBaseQuerySource": {
    object (KnowledgeBaseQuerySource)
  },
  "documentQuerySource": {
    object (DocumentQuerySource)
  },
  "dialogflowQuerySource": {
    object (DialogflowQuerySource)
  }
  // End of list of possible types for union field query_source.
}
Fields
maxResults

integer

Maximum number of results to return. Currently, if unset, defaults to 10. And the max number is 20.

confidenceThreshold

number

Confidence threshold of query result.

Agent Assist gives each suggestion a score in the range [0.0, 1.0], based on the relevance between the suggestion and the current conversation context. A score of 0.0 has no relevance, while a score of 1.0 has high relevance. Only suggestions with a score greater than or equal to the value of this field are included in the results.

For a baseline model (the default), the recommended value is in the range [0.05, 0.1].

For a custom model, there is no recommended value. Tune this value by starting from a very low value and slowly increasing until you have desired results.

If this field is not set, it is default to 0.0, which means that all suggestions are returned.

Supported features: ARTICLE_SUGGESTION, FAQ, SMART_REPLY, SMART_COMPOSE.

contextFilterSettings

object (ContextFilterSettings)

Determines how recent conversation context is filtered when generating suggestions. If unspecified, no messages will be dropped.

Union field query_source. Source of query. query_source can be only one of the following:
knowledgeBaseQuerySource

object (KnowledgeBaseQuerySource)

Query from knowledgebase. It is used by: ARTICLE_SUGGESTION, FAQ.

documentQuerySource

object (DocumentQuerySource)

Query from knowledge base document. It is used by: SMART_REPLY, SMART_COMPOSE.

dialogflowQuerySource

object (DialogflowQuerySource)

Query from Dialogflow agent. It is used by DIALOGFLOW_ASSIST.

KnowledgeBaseQuerySource

Knowledge base source settings.

Supported features: ARTICLE_SUGGESTION, FAQ.

JSON representation
{
  "knowledgeBases": [
    string
  ]
}
Fields
knowledgeBases[]

string

Required. Knowledge bases to query. Format: projects/<Project ID>/locations/<Location ID>/knowledgeBases/<Knowledge Base ID>. Currently, only one knowledge base is supported.

DocumentQuerySource

Document source settings.

Supported features: SMART_REPLY, SMART_COMPOSE.

JSON representation
{
  "documents": [
    string
  ]
}
Fields
documents[]

string

Required. Knowledge documents to query from. Format: projects/<Project ID>/locations/<Location ID>/knowledgeBases/<KnowledgeBase ID>/documents/<Document ID>. Currently, only one document is supported.

DialogflowQuerySource

Dialogflow source setting.

Supported feature: DIALOGFLOW_ASSIST.

JSON representation
{
  "agent": string
}
Fields
agent

string

Required. The name of a dialogflow virtual agent used for end user side intent detection and suggestion. Format: projects/<Project Number / ID>/locations/<Location ID>/agent. When multiple agents are allowed in the same Dialogflow project.

ContextFilterSettings

Settings that determine how to filter recent conversation context when generating suggestions.

JSON representation
{
  "dropHandoffMessages": boolean,
  "dropVirtualAgentMessages": boolean,
  "dropIvrMessages": boolean
}
Fields
dropHandoffMessages

boolean

If set to true, the last message from virtual agent (hand off message) and the message before it (trigger message of hand off) are dropped.

dropVirtualAgentMessages

boolean

If set to true, all messages from virtual agent are dropped.

dropIvrMessages

boolean

If set to true, all messages from ivr stage are dropped.

ConversationModelConfig

Custom conversation models used in agent assist feature.

Supported feature: ARTICLE_SUGGESTION, SMART_COMPOSE, SMART_REPLY.

JSON representation
{
  "model": string
}
Fields
model

string

Required. Conversation model resource name. Format: projects/<Project ID>/conversationModels/<Model ID>.

MessageAnalysisConfig

Configuration for analyses to run on each conversation message.

JSON representation
{
  "enableEntityExtraction": boolean,
  "enableSentimentAnalysis": boolean
}
Fields
enableEntityExtraction

boolean

Enable entity extraction in conversation messages on agent assist stage. If unspecified, defaults to false.

Currently, this feature is not general available, please contact Google to get access.

enableSentimentAnalysis

boolean

Enable sentiment analysis in conversation messages on agent assist stage. If unspecified, defaults to false. Sentiment analysis inspects user input and identifies the prevailing subjective opinion, especially to determine a user's attitude as positive, negative, or neutral: https://cloud.google.com/natural-language/docs/basics#sentimentAnalysis For Participants.StreamingAnalyzeContent method, result will be in StreamingAnalyzeContentResponse.message.SentimentAnalysisResult. For Participants.AnalyzeContent method, result will be in AnalyzeContentResponse.message.SentimentAnalysisResult For Conversations.ListMessages method, result will be in ListMessagesResponse.messages.SentimentAnalysisResult If Pub/Sub notification is configured, result will be in ConversationEvent.new_message_payload.SentimentAnalysisResult.

HumanAgentHandoffConfig

Defines the hand off to a live agent, typically on which external agent service provider to connect to a conversation.

Currently, this feature is not general available, please contact Google to get access.

JSON representation
{

  // Union field agent_service can be only one of the following:
  "livePersonConfig": {
    object (LivePersonConfig)
  },
  "salesforceLiveAgentConfig": {
    object (SalesforceLiveAgentConfig)
  }
  // End of list of possible types for union field agent_service.
}
Fields
Union field agent_service. Required. Specifies which agent service to connect for human agent handoff. agent_service can be only one of the following:
livePersonConfig

object (LivePersonConfig)

Uses LivePerson (https://www.liveperson.com).

salesforceLiveAgentConfig

object (SalesforceLiveAgentConfig)

Uses Salesforce Live Agent.

LivePersonConfig

Configuration specific to LivePerson (https://www.liveperson.com).

JSON representation
{
  "accountNumber": string
}
Fields
accountNumber

string

Required. Account number of the LivePerson account to connect. This is the account number you input at the login page.

SalesforceLiveAgentConfig

Configuration specific to Salesforce Live Agent.

JSON representation
{
  "organizationId": string,
  "deploymentId": string,
  "buttonId": string,
  "endpointDomain": string
}
Fields
organizationId

string

Required. The organization ID of the Salesforce account.

deploymentId

string

Required. Live Agent deployment ID.

buttonId

string

Required. Live Agent chat button ID.

endpointDomain

string

Required. Domain of the Live Agent endpoint for this agent. You can find the endpoint URL in the Live Agent settings page. For example if URL has the form https://d.la4-c2-phx.salesforceliveagent.com/..., you should fill in d.la4-c2-phx.salesforceliveagent.com.

LoggingConfig

Defines logging behavior for conversation lifecycle events.

JSON representation
{
  "enableStackdriverLogging": boolean
}
Fields
enableStackdriverLogging

boolean

Whether to log conversation events like CONVERSATION_STARTED to Stackdriver in the conversation project as JSON format ConversationEvent protos.

SpeechToTextConfig

Configures speech transcription for ConversationProfile.

JSON representation
{
  "speechModelVariant": enum (SpeechModelVariant)
}
Fields
speechModelVariant

enum (SpeechModelVariant)

Optional. The speech model used in speech to text. SPEECH_MODEL_VARIANT_UNSPECIFIED, USE_BEST_AVAILABLE will be treated as USE_ENHANCED. It can be overridden in AnalyzeContentRequest and StreamingAnalyzeContentRequest request.

SpeechModelVariant

Variant of the specified Speech model to use.

See the Cloud Speech documentation for which models have different variants. For example, the "phone_call" model has both a standard and an enhanced variant. When you use an enhanced model, you will generally receive higher quality results than for a standard model.

Enums
SPEECH_MODEL_VARIANT_UNSPECIFIED No model variant specified. In this case Dialogflow defaults to USE_BEST_AVAILABLE.
USE_BEST_AVAILABLE

Use the best available variant of the [Speech model][InputAudioConfig.model] that the caller is eligible for.

Please see the Dialogflow docs for how to make your project eligible for enhanced models.

USE_STANDARD Use standard model variant even if an enhanced model is available. See the Cloud Speech documentation for details about enhanced models.
USE_ENHANCED

Use an enhanced model variant:

  • If an enhanced variant does not exist for the given model and request language, Dialogflow falls back to the standard variant.

The Cloud Speech documentation describes which models have enhanced variants.

  • If the API caller isn't eligible for enhanced models, Dialogflow returns an error. Please see the Dialogflow docs for how to make your project eligible.

Methods

create

Creates a conversation profile in the specified project.

delete

Deletes the specified conversation profile.

get

Retrieves the specified conversation profile.

list

Returns the list of all conversation profiles in the specified project.

patch

Updates the specified conversation profile.