Detect Intent
|
|||||
|
|
Processes a natural language query and returns structured, actionable data as a result. This method is not idempotent, because it may cause contexts and session entity types to be updated, which in turn might affect results of future queries
Authorization
To use this building block you will have to grant access to at least one of the following scopes:
- View and manage your data across Google Cloud Platform services
- View, manage and query your Dialogflow agents
Input
This building block consumes 48 input parameters
Name | Format | Description |
---|---|---|
session Required |
STRING |
Required. The name of the session this query is sent to. Format:
|
queryInput |
OBJECT |
Represents the query input. It can contain either:
|
queryInput.audioConfig |
OBJECT |
Instructs the speech recognizer how to process the audio content |
queryInput.audioConfig.audioEncoding |
ENUMERATION |
Required. Audio encoding of the audio content to process |
queryInput.audioConfig.singleUtterance |
BOOLEAN |
Optional. If |
queryInput.audioConfig.languageCode |
STRING |
Required. 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 |
queryInput.audioConfig.phraseHints[] |
STRING |
|
queryInput.audioConfig.sampleRateHertz |
INTEGER |
Required. Sample rate (in Hertz) of the audio content sent in the query. Refer to Cloud Speech API documentation for more details |
queryInput.audioConfig.modelVariant |
ENUMERATION |
Optional. Which variant of the Speech model to use |
queryInput.event |
OBJECT |
Events allow for matching intents by event name instead of the natural
language input. For instance, input |
queryInput.event.languageCode |
STRING |
Required. The language of this query. 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 |
queryInput.event.name |
STRING |
Required. The unique identifier of the event |
queryInput.event.parameters |
OBJECT |
Optional. The collection of parameters associated with the event |
queryInput.event.parameters.customKey.value Required |
ANY |
Optional. The collection of parameters associated with the event |
queryInput.text |
OBJECT |
Represents the natural language text to be processed |
queryInput.text.text |
STRING |
Required. The UTF-8 encoded natural language text to be processed. Text length must not exceed 256 characters |
queryInput.text.languageCode |
STRING |
Required. The language of this conversational query. 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 |
queryParams |
OBJECT |
Represents the parameters of the conversational query |
queryParams.sessionEntityTypes[] |
OBJECT |
Represents a session entity type. Extends or replaces a developer entity type at the user session level (we refer to the entity types defined at the agent level as "developer entity types"). Note: session entity types apply to all queries, regardless of the language |
queryParams.sessionEntityTypes[].name |
STRING |
Required. The unique identifier of this session entity type. Format:
|
queryParams.sessionEntityTypes[].entityOverrideMode |
ENUMERATION |
Required. Indicates whether the additional data should override or supplement the developer entity type definition |
queryParams.sessionEntityTypes[].entities[] |
OBJECT |
An entity entry for an associated entity type |
queryParams.payload |
OBJECT |
Optional. This field can be used to pass custom data into the webhook associated with the agent. Arbitrary JSON objects are supported |
queryParams.payload.customKey.value Required |
ANY |
Optional. This field can be used to pass custom data into the webhook associated with the agent. Arbitrary JSON objects are supported |
queryParams.geoLocation |
OBJECT |
An object representing a latitude/longitude pair. This is expressed as a pair of doubles representing degrees latitude and degrees longitude. Unless specified otherwise, this must conform to the WGS84 standard. Values must be within normalized ranges |
queryParams.geoLocation.longitude |
NUMBER |
The longitude in degrees. It must be in the range [-180.0, +180.0] |
queryParams.geoLocation.latitude |
NUMBER |
The latitude in degrees. It must be in the range [-90.0, +90.0] |
queryParams.resetContexts |
BOOLEAN |
Optional. Specifies whether to delete all contexts in the current session before the new ones are activated |
queryParams.contexts[] |
OBJECT |
Represents a context |
queryParams.contexts[].lifespanCount |
INTEGER |
Optional. The number of conversational query requests after which the
context expires. If set to |
queryParams.contexts[].name |
STRING |
Required. The unique identifier of the context. Format:
The |
queryParams.contexts[].parameters |
OBJECT |
Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryParams.contexts[].parameters.customKey.value Required |
ANY |
Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryParams.sentimentAnalysisRequestConfig |
OBJECT |
Configures the types of sentiment analysis to perform |
queryParams.sentimentAnalysisRequestConfig.analyzeQueryTextSentiment |
BOOLEAN |
Optional. Instructs the service to perform sentiment analysis on
|
queryParams.timeZone |
STRING |
Optional. The time zone of this conversational query from the time zone database, e.g., America/New_York, Europe/Paris. If not provided, the time zone specified in agent settings is used |
outputAudioConfig |
OBJECT |
Instructs the speech synthesizer on how to generate the output audio content |
outputAudioConfig.audioEncoding |
ENUMERATION |
Required. Audio encoding of the synthesized audio content |
outputAudioConfig.synthesizeSpeechConfig |
OBJECT |
Configuration of how speech should be synthesized |
outputAudioConfig.synthesizeSpeechConfig.speakingRate |
NUMBER |
Optional. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal native speed supported by the specific voice. 2.0 is twice as fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any other values < 0.25 or > 4.0 will return an error |
outputAudioConfig.synthesizeSpeechConfig.effectsProfileId[] |
STRING |
|
outputAudioConfig.synthesizeSpeechConfig.volumeGainDb |
NUMBER |
Optional. Volume gain (in dB) of the normal native volume supported by the specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB) will play at approximately half the amplitude of the normal native signal amplitude. A value of +6.0 (dB) will play at approximately twice the amplitude of the normal native signal amplitude. We strongly recommend not to exceed +10 (dB) as there's usually no effective increase in loudness for any value greater than that |
outputAudioConfig.synthesizeSpeechConfig.pitch |
NUMBER |
Optional. Speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20 semitones from the original pitch. -20 means decrease 20 semitones from the original pitch |
outputAudioConfig.synthesizeSpeechConfig.voice |
OBJECT |
Description of which voice to use for speech synthesis |
outputAudioConfig.synthesizeSpeechConfig.voice.name |
STRING |
Optional. The name of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and gender |
outputAudioConfig.synthesizeSpeechConfig.voice.ssmlGender |
ENUMERATION |
Optional. The preferred gender of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and name. Note that this is only a preference, not requirement. If a voice of the appropriate gender is not available, the synthesizer should substitute a voice with a different gender rather than failing the request |
outputAudioConfig.sampleRateHertz |
INTEGER |
Optional. The synthesis sample rate (in hertz) for this audio. If not provided, then the synthesizer will use the default sample rate based on the audio encoding. If this is different from the voice's natural sample rate, then the synthesizer will honor this request by converting to the desired sample rate (which might result in worse audio quality) |
inputAudio |
BINARY |
Optional. The natural language speech audio to be processed. This field
should be populated iff |
= Parameter name
= Format
session STRING Required Required. The name of the session this query is sent to. Format:
|
queryInput OBJECT Represents the query input. It can contain either:
|
queryInput.audioConfig OBJECT Instructs the speech recognizer how to process the audio content |
queryInput.audioConfig.audioEncoding ENUMERATION Required. Audio encoding of the audio content to process |
queryInput.audioConfig.singleUtterance BOOLEAN Optional. If |
queryInput.audioConfig.languageCode STRING Required. 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 |
queryInput.audioConfig.phraseHints[] STRING |
queryInput.audioConfig.sampleRateHertz INTEGER Required. Sample rate (in Hertz) of the audio content sent in the query. Refer to Cloud Speech API documentation for more details |
queryInput.audioConfig.modelVariant ENUMERATION Optional. Which variant of the Speech model to use |
queryInput.event OBJECT Events allow for matching intents by event name instead of the natural
language input. For instance, input |
queryInput.event.languageCode STRING Required. The language of this query. 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 |
queryInput.event.name STRING Required. The unique identifier of the event |
queryInput.event.parameters OBJECT Optional. The collection of parameters associated with the event |
queryInput.event.parameters.customKey.value ANY Required Optional. The collection of parameters associated with the event |
queryInput.text OBJECT Represents the natural language text to be processed |
queryInput.text.text STRING Required. The UTF-8 encoded natural language text to be processed. Text length must not exceed 256 characters |
queryInput.text.languageCode STRING Required. The language of this conversational query. 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 |
queryParams OBJECT Represents the parameters of the conversational query |
queryParams.sessionEntityTypes[] OBJECT Represents a session entity type. Extends or replaces a developer entity type at the user session level (we refer to the entity types defined at the agent level as "developer entity types"). Note: session entity types apply to all queries, regardless of the language |
queryParams.sessionEntityTypes[].name STRING Required. The unique identifier of this session entity type. Format:
|
queryParams.sessionEntityTypes[].entityOverrideMode ENUMERATION Required. Indicates whether the additional data should override or supplement the developer entity type definition |
queryParams.sessionEntityTypes[].entities[] OBJECT An entity entry for an associated entity type |
queryParams.payload OBJECT Optional. This field can be used to pass custom data into the webhook associated with the agent. Arbitrary JSON objects are supported |
queryParams.payload.customKey.value ANY Required Optional. This field can be used to pass custom data into the webhook associated with the agent. Arbitrary JSON objects are supported |
queryParams.geoLocation OBJECT An object representing a latitude/longitude pair. This is expressed as a pair of doubles representing degrees latitude and degrees longitude. Unless specified otherwise, this must conform to the WGS84 standard. Values must be within normalized ranges |
queryParams.geoLocation.longitude NUMBER The longitude in degrees. It must be in the range [-180.0, +180.0] |
queryParams.geoLocation.latitude NUMBER The latitude in degrees. It must be in the range [-90.0, +90.0] |
queryParams.resetContexts BOOLEAN Optional. Specifies whether to delete all contexts in the current session before the new ones are activated |
queryParams.contexts[] OBJECT Represents a context |
queryParams.contexts[].lifespanCount INTEGER Optional. The number of conversational query requests after which the
context expires. If set to |
queryParams.contexts[].name STRING Required. The unique identifier of the context. Format:
The |
queryParams.contexts[].parameters OBJECT Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryParams.contexts[].parameters.customKey.value ANY Required Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryParams.sentimentAnalysisRequestConfig OBJECT Configures the types of sentiment analysis to perform |
queryParams.sentimentAnalysisRequestConfig.analyzeQueryTextSentiment BOOLEAN Optional. Instructs the service to perform sentiment analysis on
|
queryParams.timeZone STRING Optional. The time zone of this conversational query from the time zone database, e.g., America/New_York, Europe/Paris. If not provided, the time zone specified in agent settings is used |
outputAudioConfig OBJECT Instructs the speech synthesizer on how to generate the output audio content |
outputAudioConfig.audioEncoding ENUMERATION Required. Audio encoding of the synthesized audio content |
outputAudioConfig.synthesizeSpeechConfig OBJECT Configuration of how speech should be synthesized |
outputAudioConfig.synthesizeSpeechConfig.speakingRate NUMBER Optional. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal native speed supported by the specific voice. 2.0 is twice as fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any other values < 0.25 or > 4.0 will return an error |
outputAudioConfig.synthesizeSpeechConfig.effectsProfileId[] STRING |
outputAudioConfig.synthesizeSpeechConfig.volumeGainDb NUMBER Optional. Volume gain (in dB) of the normal native volume supported by the specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB) will play at approximately half the amplitude of the normal native signal amplitude. A value of +6.0 (dB) will play at approximately twice the amplitude of the normal native signal amplitude. We strongly recommend not to exceed +10 (dB) as there's usually no effective increase in loudness for any value greater than that |
outputAudioConfig.synthesizeSpeechConfig.pitch NUMBER Optional. Speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20 semitones from the original pitch. -20 means decrease 20 semitones from the original pitch |
outputAudioConfig.synthesizeSpeechConfig.voice OBJECT Description of which voice to use for speech synthesis |
outputAudioConfig.synthesizeSpeechConfig.voice.name STRING Optional. The name of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and gender |
outputAudioConfig.synthesizeSpeechConfig.voice.ssmlGender ENUMERATION Optional. The preferred gender of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and name. Note that this is only a preference, not requirement. If a voice of the appropriate gender is not available, the synthesizer should substitute a voice with a different gender rather than failing the request |
outputAudioConfig.sampleRateHertz INTEGER Optional. The synthesis sample rate (in hertz) for this audio. If not provided, then the synthesizer will use the default sample rate based on the audio encoding. If this is different from the voice's natural sample rate, then the synthesizer will honor this request by converting to the desired sample rate (which might result in worse audio quality) |
inputAudio BINARY Optional. The natural language speech audio to be processed. This field
should be populated iff |
Output
This building block provides 109 output parameters
Name | Format | Description |
---|---|---|
outputAudioConfig |
OBJECT |
Instructs the speech synthesizer on how to generate the output audio content |
outputAudioConfig.audioEncoding |
ENUMERATION |
Required. Audio encoding of the synthesized audio content |
outputAudioConfig.synthesizeSpeechConfig |
OBJECT |
Configuration of how speech should be synthesized |
outputAudioConfig.synthesizeSpeechConfig.speakingRate |
NUMBER |
Optional. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal native speed supported by the specific voice. 2.0 is twice as fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any other values < 0.25 or > 4.0 will return an error |
outputAudioConfig.synthesizeSpeechConfig.effectsProfileId[] |
STRING |
|
outputAudioConfig.synthesizeSpeechConfig.volumeGainDb |
NUMBER |
Optional. Volume gain (in dB) of the normal native volume supported by the specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB) will play at approximately half the amplitude of the normal native signal amplitude. A value of +6.0 (dB) will play at approximately twice the amplitude of the normal native signal amplitude. We strongly recommend not to exceed +10 (dB) as there's usually no effective increase in loudness for any value greater than that |
outputAudioConfig.synthesizeSpeechConfig.pitch |
NUMBER |
Optional. Speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20 semitones from the original pitch. -20 means decrease 20 semitones from the original pitch |
outputAudioConfig.synthesizeSpeechConfig.voice |
OBJECT |
Description of which voice to use for speech synthesis |
outputAudioConfig.synthesizeSpeechConfig.voice.name |
STRING |
Optional. The name of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and gender |
outputAudioConfig.synthesizeSpeechConfig.voice.ssmlGender |
ENUMERATION |
Optional. The preferred gender of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and name. Note that this is only a preference, not requirement. If a voice of the appropriate gender is not available, the synthesizer should substitute a voice with a different gender rather than failing the request |
outputAudioConfig.sampleRateHertz |
INTEGER |
Optional. The synthesis sample rate (in hertz) for this audio. If not provided, then the synthesizer will use the default sample rate based on the audio encoding. If this is different from the voice's natural sample rate, then the synthesizer will honor this request by converting to the desired sample rate (which might result in worse audio quality) |
queryResult |
OBJECT |
Represents the result of conversational query or event processing |
queryResult.webhookSource |
STRING |
If the query was fulfilled by a webhook call, this field is set to the
value of the |
queryResult.fulfillmentText |
STRING |
The text to be pronounced to the user or shown on the screen.
Note: This is a legacy field, |
queryResult.parameters |
OBJECT |
The collection of extracted parameters |
queryResult.parameters.customKey.value |
ANY |
The collection of extracted parameters |
queryResult.sentimentAnalysisResult |
OBJECT |
The result of sentiment analysis as configured by
|
queryResult.sentimentAnalysisResult.queryTextSentiment |
OBJECT |
The sentiment, such as positive/negative feeling or association, for a unit of analysis, such as the query text |
queryResult.sentimentAnalysisResult.queryTextSentiment.score |
FLOAT |
Sentiment score between -1.0 (negative sentiment) and 1.0 (positive sentiment) |
queryResult.sentimentAnalysisResult.queryTextSentiment.magnitude |
FLOAT |
A non-negative number in the [0, +inf) range, which represents the absolute magnitude of sentiment, regardless of score (positive or negative) |
queryResult.intentDetectionConfidence |
FLOAT |
The intent detection confidence. Values range from 0.0
(completely uncertain) to 1.0 (completely certain).
If there are |
queryResult.allRequiredParamsPresent |
BOOLEAN |
This field is set to:
|
queryResult.speechRecognitionConfidence |
FLOAT |
The Speech recognition confidence between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is not guaranteed to be accurate or set. In particular this field isn't set for StreamingDetectIntent since the streaming endpoint has separate confidence estimates per portion of the audio in StreamingRecognitionResult |
queryResult.queryText |
STRING |
The original conversational query text:
|
queryResult.diagnosticInfo |
OBJECT |
The free-form diagnostic info. For example, this field could contain webhook call latency. The string keys of the Struct's fields map can change without notice |
queryResult.diagnosticInfo.customKey.value |
ANY |
The free-form diagnostic info. For example, this field could contain webhook call latency. The string keys of the Struct's fields map can change without notice |
queryResult.outputContexts[] |
OBJECT |
Represents a context |
queryResult.outputContexts[].lifespanCount |
INTEGER |
Optional. The number of conversational query requests after which the
context expires. If set to |
queryResult.outputContexts[].name |
STRING |
Required. The unique identifier of the context. Format:
The |
queryResult.outputContexts[].parameters |
OBJECT |
Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryResult.outputContexts[].parameters.customKey.value |
ANY |
Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryResult.intent |
OBJECT |
Represents an intent. Intents convert a number of user expressions or patterns into an action. An action is an extraction of a user command or sentence semantics |
queryResult.intent.outputContexts[] |
OBJECT |
Represents a context |
queryResult.intent.outputContexts[].lifespanCount |
INTEGER |
Optional. The number of conversational query requests after which the
context expires. If set to |
queryResult.intent.outputContexts[].name |
STRING |
Required. The unique identifier of the context. Format:
The |
queryResult.intent.outputContexts[].parameters |
OBJECT |
Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryResult.intent.outputContexts[].parameters.customKey.value |
ANY |
Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryResult.intent.defaultResponsePlatforms[] |
ENUMERATION |
|
queryResult.intent.action |
STRING |
Optional. The name of the action associated with the intent. Note: The action name must not contain whitespaces |
queryResult.intent.name |
STRING |
The unique identifier of this intent.
Required for Intents.UpdateIntent and Intents.BatchUpdateIntents
methods.
Format: |
queryResult.intent.messages[] |
OBJECT |
Corresponds to the |
queryResult.intent.messages[].payload |
OBJECT |
Returns a response containing a custom, platform-specific payload. See the Intent.Message.Platform type for a description of the structure that may be required for your platform |
queryResult.intent.messages[].payload.customKey.value |
ANY |
Returns a response containing a custom, platform-specific payload. See the Intent.Message.Platform type for a description of the structure that may be required for your platform |
queryResult.intent.messages[].platform |
ENUMERATION |
Optional. The platform that this message is intended for |
queryResult.intent.inputContextNames[] |
STRING |
|
queryResult.intent.webhookState |
ENUMERATION |
Optional. Indicates whether webhooks are enabled for the intent |
queryResult.intent.followupIntentInfo[] |
OBJECT |
Represents a single followup intent in the chain |
queryResult.intent.followupIntentInfo[].followupIntentName |
STRING |
The unique identifier of the followup intent.
Format: |
queryResult.intent.followupIntentInfo[].parentFollowupIntentName |
STRING |
The unique identifier of the followup intent's parent.
Format: |
queryResult.intent.displayName |
STRING |
Required. The name of this intent |
queryResult.intent.rootFollowupIntentName |
STRING |
Read-only. The unique identifier of the root intent in the chain of followup intents. It identifies the correct followup intents chain for this intent. We populate this field only in the output. Format: |
queryResult.intent.mlDisabled |
BOOLEAN |
Optional. Indicates whether Machine Learning is disabled for the intent.
Note: If |
queryResult.intent.isFallback |
BOOLEAN |
Optional. Indicates whether this is a fallback intent |
queryResult.intent.parameters[] |
OBJECT |
Represents intent parameters |
queryResult.intent.parameters[].entityTypeDisplayName |
STRING |
Optional. The name of the entity type, prefixed with |
queryResult.intent.parameters[].prompts[] |
STRING |
|
queryResult.intent.parameters[].defaultValue |
STRING |
Optional. The default value to use when the |
queryResult.intent.parameters[].mandatory |
BOOLEAN |
Optional. Indicates whether the parameter is required. That is, whether the intent cannot be completed without collecting the parameter value |
queryResult.intent.parameters[].name |
STRING |
The unique identifier of this parameter |
queryResult.intent.parameters[].isList |
BOOLEAN |
Optional. Indicates whether the parameter represents a list of values |
queryResult.intent.parameters[].value |
STRING |
Optional. The definition of the parameter value. It can be:
|
queryResult.intent.parameters[].displayName |
STRING |
Required. The name of the parameter |
queryResult.intent.resetContexts |
BOOLEAN |
Optional. Indicates whether to delete all contexts in the current session when this intent is matched |
queryResult.intent.trainingPhrases[] |
OBJECT |
Represents an example that the agent is trained on |
queryResult.intent.trainingPhrases[].timesAddedCount |
INTEGER |
Optional. Indicates how many times this example was added to the intent. Each time a developer adds an existing sample by editing an intent or training, this counter is increased |
queryResult.intent.trainingPhrases[].type |
ENUMERATION |
Required. The type of the training phrase |
queryResult.intent.trainingPhrases[].name |
STRING |
Output only. The unique identifier of this training phrase |
queryResult.intent.parentFollowupIntentName |
STRING |
Read-only after creation. The unique identifier of the parent intent in the chain of followup intents. You can set this field when creating an intent, for example with CreateIntent or BatchUpdateIntents, in order to make this intent a followup intent. It identifies the parent followup intent.
Format: |
queryResult.intent.events[] |
STRING |
|
queryResult.intent.priority |
INTEGER |
Optional. The priority of this intent. Higher numbers represent higher priorities. If this is zero or unspecified, we use the default priority 500000. Negative numbers mean that the intent is disabled |
queryResult.languageCode |
STRING |
The language that was triggered during intent detection. See Language Support for a list of the currently supported language codes |
queryResult.webhookPayload |
OBJECT |
If the query was fulfilled by a webhook call, this field is set to the
value of the |
queryResult.webhookPayload.customKey.value |
ANY |
If the query was fulfilled by a webhook call, this field is set to the
value of the |
queryResult.fulfillmentMessages[] |
OBJECT |
Corresponds to the |
queryResult.fulfillmentMessages[].listSelect |
OBJECT |
The card for presenting a list of options to select from |
queryResult.fulfillmentMessages[].listSelect.title |
STRING |
Optional. The overall title of the list |
queryResult.fulfillmentMessages[].quickReplies |
OBJECT |
The quick replies response message |
queryResult.fulfillmentMessages[].quickReplies.quickReplies[] |
STRING |
|
queryResult.fulfillmentMessages[].quickReplies.title |
STRING |
Optional. The title of the collection of quick replies |
queryResult.fulfillmentMessages[].card |
OBJECT |
The card response message |
queryResult.fulfillmentMessages[].card.title |
STRING |
Optional. The title of the card |
queryResult.fulfillmentMessages[].card.subtitle |
STRING |
Optional. The subtitle of the card |
queryResult.fulfillmentMessages[].card.imageUri |
STRING |
Optional. The public URI to an image file for the card |
queryResult.fulfillmentMessages[].basicCard |
OBJECT |
The basic card message. Useful for displaying information |
queryResult.fulfillmentMessages[].basicCard.title |
STRING |
Optional. The title of the card |
queryResult.fulfillmentMessages[].basicCard.formattedText |
STRING |
Required, unless image is present. The body text of the card |
queryResult.fulfillmentMessages[].basicCard.subtitle |
STRING |
Optional. The subtitle of the card |
queryResult.fulfillmentMessages[].carouselSelect |
OBJECT |
The card for presenting a carousel of options to select from |
queryResult.fulfillmentMessages[].linkOutSuggestion |
OBJECT |
The suggestion chip message that allows the user to jump out to the app or website associated with this agent |
queryResult.fulfillmentMessages[].linkOutSuggestion.destinationName |
STRING |
Required. The name of the app or site this chip is linking to |
queryResult.fulfillmentMessages[].linkOutSuggestion.uri |
STRING |
Required. The URI of the app or site to open when the user taps the suggestion chip |
queryResult.fulfillmentMessages[].simpleResponses |
OBJECT |
The collection of simple response candidates.
This message in |
queryResult.fulfillmentMessages[].image |
OBJECT |
The image response message |
queryResult.fulfillmentMessages[].image.imageUri |
STRING |
Optional. The public URI to an image file |
queryResult.fulfillmentMessages[].image.accessibilityText |
STRING |
Optional. A text description of the image to be used for accessibility, e.g., screen readers |
queryResult.fulfillmentMessages[].payload |
OBJECT |
Returns a response containing a custom, platform-specific payload. See the Intent.Message.Platform type for a description of the structure that may be required for your platform |
queryResult.fulfillmentMessages[].payload.customKey.value |
ANY |
Returns a response containing a custom, platform-specific payload. See the Intent.Message.Platform type for a description of the structure that may be required for your platform |
queryResult.fulfillmentMessages[].text |
OBJECT |
The text response message |
queryResult.fulfillmentMessages[].text.text[] |
STRING |
|
queryResult.fulfillmentMessages[].platform |
ENUMERATION |
Optional. The platform that this message is intended for |
queryResult.fulfillmentMessages[].suggestions |
OBJECT |
The collection of suggestions |
queryResult.action |
STRING |
The action name from the matched intent |
outputAudio |
BINARY |
The audio data bytes encoded as specified in the request.
Note: The output audio is generated based on the values of default platform
text responses found in the |
webhookStatus |
OBJECT |
The You can find out more about this error model and how to work with it in the API Design Guide |
webhookStatus.code |
INTEGER |
The status code, which should be an enum value of google.rpc.Code |
webhookStatus.message |
STRING |
A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client |
webhookStatus.details[] |
OBJECT |
|
webhookStatus.details[].customKey.value |
ANY |
|
responseId |
STRING |
The unique identifier of the response. It can be used to locate a response in the training example set or for reporting issues |
= Parameter name
= Format
outputAudioConfig OBJECT Instructs the speech synthesizer on how to generate the output audio content |
outputAudioConfig.audioEncoding ENUMERATION Required. Audio encoding of the synthesized audio content |
outputAudioConfig.synthesizeSpeechConfig OBJECT Configuration of how speech should be synthesized |
outputAudioConfig.synthesizeSpeechConfig.speakingRate NUMBER Optional. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal native speed supported by the specific voice. 2.0 is twice as fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any other values < 0.25 or > 4.0 will return an error |
outputAudioConfig.synthesizeSpeechConfig.effectsProfileId[] STRING |
outputAudioConfig.synthesizeSpeechConfig.volumeGainDb NUMBER Optional. Volume gain (in dB) of the normal native volume supported by the specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB) will play at approximately half the amplitude of the normal native signal amplitude. A value of +6.0 (dB) will play at approximately twice the amplitude of the normal native signal amplitude. We strongly recommend not to exceed +10 (dB) as there's usually no effective increase in loudness for any value greater than that |
outputAudioConfig.synthesizeSpeechConfig.pitch NUMBER Optional. Speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20 semitones from the original pitch. -20 means decrease 20 semitones from the original pitch |
outputAudioConfig.synthesizeSpeechConfig.voice OBJECT Description of which voice to use for speech synthesis |
outputAudioConfig.synthesizeSpeechConfig.voice.name STRING Optional. The name of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and gender |
outputAudioConfig.synthesizeSpeechConfig.voice.ssmlGender ENUMERATION Optional. The preferred gender of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and name. Note that this is only a preference, not requirement. If a voice of the appropriate gender is not available, the synthesizer should substitute a voice with a different gender rather than failing the request |
outputAudioConfig.sampleRateHertz INTEGER Optional. The synthesis sample rate (in hertz) for this audio. If not provided, then the synthesizer will use the default sample rate based on the audio encoding. If this is different from the voice's natural sample rate, then the synthesizer will honor this request by converting to the desired sample rate (which might result in worse audio quality) |
queryResult OBJECT Represents the result of conversational query or event processing |
queryResult.webhookSource STRING If the query was fulfilled by a webhook call, this field is set to the
value of the |
queryResult.fulfillmentText STRING The text to be pronounced to the user or shown on the screen.
Note: This is a legacy field, |
queryResult.parameters OBJECT The collection of extracted parameters |
queryResult.parameters.customKey.value ANY The collection of extracted parameters |
queryResult.sentimentAnalysisResult OBJECT The result of sentiment analysis as configured by
|
queryResult.sentimentAnalysisResult.queryTextSentiment OBJECT The sentiment, such as positive/negative feeling or association, for a unit of analysis, such as the query text |
queryResult.sentimentAnalysisResult.queryTextSentiment.score FLOAT Sentiment score between -1.0 (negative sentiment) and 1.0 (positive sentiment) |
queryResult.sentimentAnalysisResult.queryTextSentiment.magnitude FLOAT A non-negative number in the [0, +inf) range, which represents the absolute magnitude of sentiment, regardless of score (positive or negative) |
queryResult.intentDetectionConfidence FLOAT The intent detection confidence. Values range from 0.0
(completely uncertain) to 1.0 (completely certain).
If there are |
queryResult.allRequiredParamsPresent BOOLEAN This field is set to:
|
queryResult.speechRecognitionConfidence FLOAT The Speech recognition confidence between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is not guaranteed to be accurate or set. In particular this field isn't set for StreamingDetectIntent since the streaming endpoint has separate confidence estimates per portion of the audio in StreamingRecognitionResult |
queryResult.queryText STRING The original conversational query text:
|
queryResult.diagnosticInfo OBJECT The free-form diagnostic info. For example, this field could contain webhook call latency. The string keys of the Struct's fields map can change without notice |
queryResult.diagnosticInfo.customKey.value ANY The free-form diagnostic info. For example, this field could contain webhook call latency. The string keys of the Struct's fields map can change without notice |
queryResult.outputContexts[] OBJECT Represents a context |
queryResult.outputContexts[].lifespanCount INTEGER Optional. The number of conversational query requests after which the
context expires. If set to |
queryResult.outputContexts[].name STRING Required. The unique identifier of the context. Format:
The |
queryResult.outputContexts[].parameters OBJECT Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryResult.outputContexts[].parameters.customKey.value ANY Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryResult.intent OBJECT Represents an intent. Intents convert a number of user expressions or patterns into an action. An action is an extraction of a user command or sentence semantics |
queryResult.intent.outputContexts[] OBJECT Represents a context |
queryResult.intent.outputContexts[].lifespanCount INTEGER Optional. The number of conversational query requests after which the
context expires. If set to |
queryResult.intent.outputContexts[].name STRING Required. The unique identifier of the context. Format:
The |
queryResult.intent.outputContexts[].parameters OBJECT Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryResult.intent.outputContexts[].parameters.customKey.value ANY Optional. The collection of parameters associated with this context. Refer to this doc for syntax |
queryResult.intent.defaultResponsePlatforms[] ENUMERATION |
queryResult.intent.action STRING Optional. The name of the action associated with the intent. Note: The action name must not contain whitespaces |
queryResult.intent.name STRING The unique identifier of this intent.
Required for Intents.UpdateIntent and Intents.BatchUpdateIntents
methods.
Format: |
queryResult.intent.messages[] OBJECT Corresponds to the |
queryResult.intent.messages[].payload OBJECT Returns a response containing a custom, platform-specific payload. See the Intent.Message.Platform type for a description of the structure that may be required for your platform |
queryResult.intent.messages[].payload.customKey.value ANY Returns a response containing a custom, platform-specific payload. See the Intent.Message.Platform type for a description of the structure that may be required for your platform |
queryResult.intent.messages[].platform ENUMERATION Optional. The platform that this message is intended for |
queryResult.intent.inputContextNames[] STRING |
queryResult.intent.webhookState ENUMERATION Optional. Indicates whether webhooks are enabled for the intent |
queryResult.intent.followupIntentInfo[] OBJECT Represents a single followup intent in the chain |
queryResult.intent.followupIntentInfo[].followupIntentName STRING The unique identifier of the followup intent.
Format: |
queryResult.intent.followupIntentInfo[].parentFollowupIntentName STRING The unique identifier of the followup intent's parent.
Format: |
queryResult.intent.displayName STRING Required. The name of this intent |
queryResult.intent.rootFollowupIntentName STRING Read-only. The unique identifier of the root intent in the chain of followup intents. It identifies the correct followup intents chain for this intent. We populate this field only in the output. Format: |
queryResult.intent.mlDisabled BOOLEAN Optional. Indicates whether Machine Learning is disabled for the intent.
Note: If |
queryResult.intent.isFallback BOOLEAN Optional. Indicates whether this is a fallback intent |
queryResult.intent.parameters[] OBJECT Represents intent parameters |
queryResult.intent.parameters[].entityTypeDisplayName STRING Optional. The name of the entity type, prefixed with |
queryResult.intent.parameters[].prompts[] STRING |
queryResult.intent.parameters[].defaultValue STRING Optional. The default value to use when the |
queryResult.intent.parameters[].mandatory BOOLEAN Optional. Indicates whether the parameter is required. That is, whether the intent cannot be completed without collecting the parameter value |
queryResult.intent.parameters[].name STRING The unique identifier of this parameter |
queryResult.intent.parameters[].isList BOOLEAN Optional. Indicates whether the parameter represents a list of values |
queryResult.intent.parameters[].value STRING Optional. The definition of the parameter value. It can be:
|
queryResult.intent.parameters[].displayName STRING Required. The name of the parameter |
queryResult.intent.resetContexts BOOLEAN Optional. Indicates whether to delete all contexts in the current session when this intent is matched |
queryResult.intent.trainingPhrases[] OBJECT Represents an example that the agent is trained on |
queryResult.intent.trainingPhrases[].timesAddedCount INTEGER Optional. Indicates how many times this example was added to the intent. Each time a developer adds an existing sample by editing an intent or training, this counter is increased |
queryResult.intent.trainingPhrases[].type ENUMERATION Required. The type of the training phrase |
queryResult.intent.trainingPhrases[].name STRING Output only. The unique identifier of this training phrase |
queryResult.intent.parentFollowupIntentName STRING Read-only after creation. The unique identifier of the parent intent in the chain of followup intents. You can set this field when creating an intent, for example with CreateIntent or BatchUpdateIntents, in order to make this intent a followup intent. It identifies the parent followup intent.
Format: |
queryResult.intent.events[] STRING |
queryResult.intent.priority INTEGER Optional. The priority of this intent. Higher numbers represent higher priorities. If this is zero or unspecified, we use the default priority 500000. Negative numbers mean that the intent is disabled |
queryResult.languageCode STRING The language that was triggered during intent detection. See Language Support for a list of the currently supported language codes |
queryResult.webhookPayload OBJECT If the query was fulfilled by a webhook call, this field is set to the
value of the |
queryResult.webhookPayload.customKey.value ANY If the query was fulfilled by a webhook call, this field is set to the
value of the |
queryResult.fulfillmentMessages[] OBJECT Corresponds to the |
queryResult.fulfillmentMessages[].listSelect OBJECT The card for presenting a list of options to select from |
queryResult.fulfillmentMessages[].listSelect.title STRING Optional. The overall title of the list |
queryResult.fulfillmentMessages[].quickReplies OBJECT The quick replies response message |
queryResult.fulfillmentMessages[].quickReplies.quickReplies[] STRING |
queryResult.fulfillmentMessages[].quickReplies.title STRING Optional. The title of the collection of quick replies |
queryResult.fulfillmentMessages[].card OBJECT The card response message |
queryResult.fulfillmentMessages[].card.title STRING Optional. The title of the card |
queryResult.fulfillmentMessages[].card.subtitle STRING Optional. The subtitle of the card |
queryResult.fulfillmentMessages[].card.imageUri STRING Optional. The public URI to an image file for the card |
queryResult.fulfillmentMessages[].basicCard OBJECT The basic card message. Useful for displaying information |
queryResult.fulfillmentMessages[].basicCard.title STRING Optional. The title of the card |
queryResult.fulfillmentMessages[].basicCard.formattedText STRING Required, unless image is present. The body text of the card |
queryResult.fulfillmentMessages[].basicCard.subtitle STRING Optional. The subtitle of the card |
queryResult.fulfillmentMessages[].carouselSelect OBJECT The card for presenting a carousel of options to select from |
queryResult.fulfillmentMessages[].linkOutSuggestion OBJECT The suggestion chip message that allows the user to jump out to the app or website associated with this agent |
queryResult.fulfillmentMessages[].linkOutSuggestion.destinationName STRING Required. The name of the app or site this chip is linking to |
queryResult.fulfillmentMessages[].linkOutSuggestion.uri STRING Required. The URI of the app or site to open when the user taps the suggestion chip |
queryResult.fulfillmentMessages[].simpleResponses OBJECT The collection of simple response candidates.
This message in |
queryResult.fulfillmentMessages[].image OBJECT The image response message |
queryResult.fulfillmentMessages[].image.imageUri STRING Optional. The public URI to an image file |
queryResult.fulfillmentMessages[].image.accessibilityText STRING Optional. A text description of the image to be used for accessibility, e.g., screen readers |
queryResult.fulfillmentMessages[].payload OBJECT Returns a response containing a custom, platform-specific payload. See the Intent.Message.Platform type for a description of the structure that may be required for your platform |
queryResult.fulfillmentMessages[].payload.customKey.value ANY Returns a response containing a custom, platform-specific payload. See the Intent.Message.Platform type for a description of the structure that may be required for your platform |
queryResult.fulfillmentMessages[].text OBJECT The text response message |
queryResult.fulfillmentMessages[].text.text[] STRING |
queryResult.fulfillmentMessages[].platform ENUMERATION Optional. The platform that this message is intended for |
queryResult.fulfillmentMessages[].suggestions OBJECT The collection of suggestions |
queryResult.action STRING The action name from the matched intent |
outputAudio BINARY The audio data bytes encoded as specified in the request.
Note: The output audio is generated based on the values of default platform
text responses found in the |
webhookStatus OBJECT The You can find out more about this error model and how to work with it in the API Design Guide |
webhookStatus.code INTEGER The status code, which should be an enum value of google.rpc.Code |
webhookStatus.message STRING A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client |
webhookStatus.details[] OBJECT |
webhookStatus.details[].customKey.value ANY |
responseId STRING The unique identifier of the response. It can be used to locate a response in the training example set or for reporting issues |