- Resource: ConversationProfile
- JSON representation
- AutomatedAgentConfig
- HumanAgentAssistantConfig
- NotificationConfig
- MessageFormat
- SuggestionConfig
- SuggestionFeatureConfig
- SuggestionFeature
- Type
- SuggestionTriggerSettings
- SuggestionQueryConfig
- KnowledgeBaseQuerySource
- DocumentQuerySource
- DialogflowQuerySource
- HumanAgentSideConfig
- ContextFilterSettings
- Sections
- SectionType
- ConversationModelConfig
- ConversationProcessConfig
- MessageAnalysisConfig
- HumanAgentHandoffConfig
- LivePersonConfig
- SalesforceLiveAgentConfig
- LoggingConfig
- SpeechToTextConfig
- SpeechModelVariant
- AudioEncoding
- Methods
Resource: ConversationProfile
Defines the services to connect to incoming Dialogflow conversations.
JSON representation |
---|
{ "name": string, "displayName": string, "createTime": string, "updateTime": string, "automatedAgentConfig": { object ( |
Fields | |
---|---|
name |
The unique identifier of this conversation profile. Format: |
display |
Required. Human readable name for this profile. Max length 1024 bytes. |
create |
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: |
update |
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: |
automated |
Configuration for an automated agent to use with this profile. |
human |
Configuration for agent assistance to use with this profile. |
human |
Configuration for connecting to a live agent. Currently, this feature is not general available, please contact Google to get access. |
notification |
Configuration for publishing conversation lifecycle events. |
logging |
Configuration for logging conversation lifecycle events. |
new |
Configuration for publishing new message events. Event will be sent in format of |
stt |
Settings for speech transcription. |
language |
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. This should be a BCP-47 language tag. Example: "en-US". |
time |
The time zone of this conversational profile from the time zone database, e.g., America/New_York, Europe/Paris. Defaults to America/New_York. |
security |
Name of the CX SecuritySettings reference for the agent. Format: |
tts |
Configuration for Text-to-Speech synthesization. Used by Phone Gateway to specify synthesization options. If agent defines synthesization options as well, agent settings overrides the option here. |
AutomatedAgentConfig
Defines the Automated Agent to connect to a conversation.
JSON representation |
---|
{ "agent": string, "sessionTtl": string } |
Fields | |
---|---|
agent |
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
|
session |
Optional. Configure lifetime of the Dialogflow session. By default, a Dialogflow CX session remains active and its data is stored for 30 minutes after the last request is sent for the session. This value should be no longer than 1 day. A duration in seconds with up to nine fractional digits, ending with ' |
HumanAgentAssistantConfig
Defines the Human Agent Assistant to connect to a conversation.
JSON representation |
---|
{ "notificationConfig": { object ( |
Fields | |
---|---|
notification |
Pub/Sub topic on which to publish new agent assistant events. |
human |
Configuration for agent assistance of human agent participant. |
end |
Configuration for agent assistance of end user participant. Currently, this feature is not general available, please contact Google to get access. |
message |
Configuration for message analysis. |
NotificationConfig
Defines notification behavior.
JSON representation |
---|
{
"topic": string,
"messageFormat": enum ( |
Fields | |
---|---|
topic |
Name of the Pub/Sub topic to publish conversation events like For telephony integration to receive notification, make sure either this topic is in the same project as the conversation or you grant For chat integration to receive notification, make sure API caller has been granted the Format: |
message |
Format of message. |
MessageFormat
Format of cloud pub/sub message.
Enums | |
---|---|
MESSAGE_FORMAT_UNSPECIFIED |
If it is unspecified, PROTO will be used. |
PROTO |
Pub/Sub message will be serialized proto. |
JSON |
Pub/Sub message will be json. |
SuggestionConfig
Detail human agent assistant config.
JSON representation |
---|
{
"featureConfigs": [
{
object ( |
Fields | |
---|---|
feature |
Configuration of different suggestion features. One feature can have only one config. |
group |
If If |
generators[] |
Optional. List of various generator resource names used in the conversation profile. |
disable |
Optional. When disableHighLatencyFeaturesSyncDelivery is true and using the AnalyzeContent API, we will not deliver the responses from high latency features in the API response. The humanAgentAssistantConfig.notification_config must be configured and enableEventBasedSuggestion must be set to true to receive the responses from high latency features in Pub/Sub. High latency feature(s): KNOWLEDGE_ASSIST |
SuggestionFeatureConfig
Config for suggestion features.
JSON representation |
---|
{ "suggestionFeature": { object ( |
Fields | |
---|---|
suggestion |
The suggestion feature. |
enable |
Automatically iterates all participants and tries to compile suggestions. Supported features: ARTICLE_SUGGESTION, FAQ, DIALOGFLOW_ASSIST, ENTITY_EXTRACTION, KNOWLEDGE_ASSIST. |
disable |
Optional. Disable the logging of search queries sent by human agents. It can prevent those queries from being stored at answer records. Supported features: KNOWLEDGE_SEARCH. |
enable |
Optional. Enable query suggestion even if we can't find its answer. By default, queries are suggested only if we find its answer. Supported features: KNOWLEDGE_ASSIST |
enable |
Optional. Enable including conversation context during query answer generation. Supported features: KNOWLEDGE_SEARCH. |
enable |
Optional. Enable query suggestion only. Supported features: KNOWLEDGE_ASSIST |
suggestion |
Settings of suggestion trigger. Currently, only ARTICLE_SUGGESTION, FAQ, and DIALOGFLOW_ASSIST will use this field. |
query |
Configs of query. |
conversation |
Configs of custom conversation model. |
conversation |
Configs for processing conversation. |
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 ( |
Fields | |
---|---|
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 for chat. |
FAQ |
Run FAQ model. |
SMART_REPLY |
Run smart reply model for chat. |
DIALOGFLOW_ASSIST |
Run Dialogflow assist model for chat, which will return automated agent response as suggestion. |
CONVERSATION_SUMMARIZATION |
Run conversation summarization model for chat. |
KNOWLEDGE_SEARCH |
Run knowledge search with text input from agent or text generated query. |
KNOWLEDGE_ASSIST |
Run knowledge assist with automatic query generation. |
SuggestionTriggerSettings
Settings of suggestion trigger.
JSON representation |
---|
{ "noSmallTalk": boolean, "onlyEndUser": boolean } |
Fields | |
---|---|
no |
Do not trigger if last utterance is small talk. |
only |
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 ( |
Fields | |
---|---|
max |
Maximum number of results to return. Currently, if unset, defaults to 10. And the max number is 20. |
confidence |
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, KNOWLEDGE_SEARCH, KNOWLEDGE_ASSIST, ENTITY_EXTRACTION. |
context |
Determines how recent conversation context is filtered when generating suggestions. If unspecified, no messages will be dropped. |
sections |
Optional. The customized sections chosen to return when requesting a summary of a conversation. |
context |
Optional. The number of recent messages to include in the context. Supported features: KNOWLEDGE_ASSIST. |
Union field query_source . Source of query. query_source can be only one of the following: |
|
knowledge |
Query from knowledgebase. It is used by: ARTICLE_SUGGESTION, FAQ. |
document |
Query from knowledge base document. It is used by: SMART_REPLY, SMART_COMPOSE. |
dialogflow |
Query from Dialogflow agent. It is used by DIALOGFLOW_ASSIST, ENTITY_EXTRACTION. |
KnowledgeBaseQuerySource
Knowledge base source settings.
Supported features: ARTICLE_SUGGESTION, FAQ.
JSON representation |
---|
{ "knowledgeBases": [ string ] } |
Fields | |
---|---|
knowledge |
Required. Knowledge bases to query. Format: |
DocumentQuerySource
Document source settings.
Supported features: SMART_REPLY, SMART_COMPOSE.
JSON representation |
---|
{ "documents": [ string ] } |
Fields | |
---|---|
documents[] |
Required. Knowledge documents to query from. Format: |
DialogflowQuerySource
Dialogflow source setting.
Supported feature: DIALOGFLOW_ASSIST, ENTITY_EXTRACTION.
JSON representation |
---|
{
"agent": string,
"humanAgentSideConfig": {
object ( |
Fields | |
---|---|
agent |
Required. The name of a dialogflow virtual agent used for end user side intent detection and suggestion. Format: |
human |
The Dialogflow assist configuration for human agent. |
HumanAgentSideConfig
The configuration used for human agent side Dialogflow assist suggestion.
JSON representation |
---|
{ "agent": string } |
Fields | |
---|---|
agent |
Optional. The name of a dialogflow virtual agent used for intent detection and suggestion triggered by human agent. Format: |
ContextFilterSettings
Settings that determine how to filter recent conversation context when generating suggestions.
JSON representation |
---|
{ "dropHandoffMessages": boolean, "dropVirtualAgentMessages": boolean, "dropIvrMessages": boolean } |
Fields | |
---|---|
drop |
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. |
drop |
If set to true, all messages from virtual agent are dropped. |
drop |
If set to true, all messages from ivr stage are dropped. |
Sections
Custom sections to return when requesting a summary of a conversation. This is only supported when baselineModelVersion
== '2.0'.
Supported features: CONVERSATION_SUMMARIZATION, CONVERSATION_SUMMARIZATION_VOICE.
JSON representation |
---|
{
"sectionTypes": [
enum ( |
Fields | |
---|---|
section |
The selected sections chosen to return when requesting a summary of a conversation. A duplicate selected section will be treated as a single selected section. If section types are not provided, the default will be {SITUATION, ACTION, RESULT}. |
SectionType
Selectable sections to return when requesting a summary of a conversation.
Enums | |
---|---|
SECTION_TYPE_UNSPECIFIED |
Undefined section type, does not return anything. |
SITUATION |
What the customer needs help with or has question about. Section name: "situation". |
ACTION |
What the agent does to help the customer. Section name: "action". |
RESOLUTION |
Result of the customer service. A single word describing the result of the conversation. Section name: "resolution". |
REASON_FOR_CANCELLATION |
Reason for cancellation if the customer requests for a cancellation. "N/A" otherwise. Section name: "reason_for_cancellation". |
CUSTOMER_SATISFACTION |
"Unsatisfied" or "Satisfied" depending on the customer's feelings at the end of the conversation. Section name: "customer_satisfaction". |
ENTITIES |
Key entities extracted from the conversation, such as ticket number, order number, dollar amount, etc. Section names are prefixed by "entities/". |
ConversationModelConfig
Custom conversation models used in agent assist feature.
Supported feature: ARTICLE_SUGGESTION, SMART_COMPOSE, SMART_REPLY, CONVERSATION_SUMMARIZATION.
JSON representation |
---|
{ "model": string, "baselineModelVersion": string } |
Fields | |
---|---|
model |
Conversation model resource name. Format: |
baseline |
Version of current baseline model. It will be ignored if |
ConversationProcessConfig
Config to process conversation.
JSON representation |
---|
{ "recentSentencesCount": integer } |
Fields | |
---|---|
recent |
Number of recent non-small-talk sentences to use as context for article and FAQ suggestion |
MessageAnalysisConfig
Configuration for analyses to run on each conversation message.
JSON representation |
---|
{ "enableEntityExtraction": boolean, "enableSentimentAnalysis": boolean } |
Fields | |
---|---|
enable |
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. |
enable |
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 |
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 |
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: |
|
live |
Uses LivePerson. |
salesforce |
Uses Salesforce Live Agent. |
LivePersonConfig
Configuration specific to LivePerson.
JSON representation |
---|
{ "accountNumber": string } |
Fields | |
---|---|
account |
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 | |
---|---|
organization |
Required. The organization ID of the Salesforce account. |
deployment |
Required. Live Agent deployment ID. |
button |
Required. Live Agent chat button ID. |
endpoint |
Required. Domain of the Live Agent endpoint for this agent. You can find the endpoint URL in the |
LoggingConfig
Defines logging behavior for conversation lifecycle events.
JSON representation |
---|
{ "enableStackdriverLogging": boolean } |
Fields | |
---|---|
enable |
Whether to log conversation events like |
SpeechToTextConfig
Configures speech transcription for ConversationProfile
.
JSON representation |
---|
{ "speechModelVariant": enum ( |
Fields | |
---|---|
speech |
The speech model used in speech to text. |
model |
Which Speech model to select. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then Dialogflow auto-selects a model based on other parameters in the SpeechToTextConfig and Agent settings. If enhanced speech model is enabled for the agent and an enhanced version of the specified model for the language does not exist, then the speech is recognized using the standard version of the specified model. Refer to Cloud Speech API documentation for more details. If you specify a model, the following models typically have the best performance:
Leave this field unspecified to use Agent Speech settings for model selection. |
audio |
Audio encoding of the audio content to process. |
sample |
Sample rate (in Hertz) of the audio content sent in the query. Refer to Cloud Speech API documentation for more details. |
language |
The language of the supplied audio. Dialogflow does not do translations. See Language Support for a list of the currently supported language codes. Note that queries in the same session do not necessarily need to specify the same language. |
enable |
If |
use |
Use timeout based endpointing, interpreting endpointer sensitivy as seconds of timeout value. |
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:
The Cloud Speech documentation describes which models have enhanced variants.
|
AudioEncoding
Audio encoding of the audio content sent in the conversational query request. Refer to the Cloud Speech API documentation for more details.
Enums | |
---|---|
AUDIO_ENCODING_UNSPECIFIED |
Not specified. |
AUDIO_ENCODING_LINEAR_16 |
Uncompressed 16-bit signed little-endian samples (Linear PCM). |
AUDIO_ENCODING_FLAC |
FLAC (Free Lossless Audio Codec) is the recommended encoding because it is lossless (therefore recognition is not compromised) and requires only about half the bandwidth of LINEAR16 . FLAC stream encoding supports 16-bit and 24-bit samples, however, not all fields in STREAMINFO are supported. |
AUDIO_ENCODING_MULAW |
8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law. |
AUDIO_ENCODING_AMR |
Adaptive Multi-Rate Narrowband codec. sampleRateHertz must be 8000. |
AUDIO_ENCODING_AMR_WB |
Adaptive Multi-Rate Wideband codec. sampleRateHertz must be 16000. |
AUDIO_ENCODING_OGG_OPUS |
Opus encoded audio frames in Ogg container (OggOpus). sampleRateHertz must be 16000. |
AUDIO_ENCODING_SPEEX_WITH_HEADER_BYTE |
Although the use of lossy encodings is not recommended, if a very low bitrate encoding is required, OGG_OPUS is highly preferred over Speex encoding. The Speex encoding supported by Dialogflow API has a header byte in each block, as in MIME type audio/x-speex-with-header-byte . It is a variant of the RTP Speex encoding defined in RFC 5574. The stream is a sequence of blocks, one block per RTP packet. Each block starts with a byte containing the length of the block, in bytes, followed by one or more frames of Speex data, padded to an integral number of bytes (octets) as specified in RFC 5574. In other words, each RTP header is replaced with a single byte containing the block length. Only Speex wideband is supported. sampleRateHertz must be 16000. |
AUDIO_ENCODING_ALAW |
8-bit samples that compand 13-bit audio samples using G.711 PCMU/a-law. |
Methods |
|
---|---|
|
Clears a suggestion feature from a conversation profile for the given participant role. |
|
Creates a conversation profile in the specified project. |
|
Deletes the specified conversation profile. |
|
Retrieves the specified conversation profile. |
|
Returns the list of all conversation profiles in the specified project. |
|
Updates the specified conversation profile. |
|
Adds or updates a suggestion feature in a conversation profile. |