Builds conversational interfaces (for example, chatbots, and voice-powered apps and devices).

Defines the root interface for all clients that generate credentials for calling Google APIs. All clients should implement this interface.

Hierarchical advanced settings for agent/flow/page/fulfillment/parameter. Settings exposed at lower level overrides the settings exposed at higher level. Overriding occurs at the sub-setting level. For example, the playback_interruption_settings at fulfillment level only overrides the playback_interruption_settings at the agent level, leaving other settings at the agent level unchanged. DTMF settings does not override each other. DTMF settings set at different levels define DTMF detections running in parallel. Hierarchy: Agent->Flow->Page->Fulfillment/Parameter.

Define behaviors for DTMF (dual tone multi frequency).

Define behaviors on logging.

Define behaviors of speech to text detection.

Agents are best described as Natural Language Understanding (NLU) modules that transform user requests into actionable data. You can include agents in your app, product, or service to determine user intent and respond to the user in a natural way. After you create an agent, you can add Intents, Entity Types, Flows, Fulfillments, Webhooks, TransitionRouteGroups and so on to manage the conversation flows.

Settings for answer feedback collection.

Settings for Gen App Builder.

Settings for connecting to Git repository for an agent.

Settings of integration with GitHub.

Settings for end user personalization.

The response message for Agents.GetAgentValidationResult.

Stores information about feedback provided by users about a response.

Stores extra information about why users provided thumbs down rating.

Represents the natural speech audio to be processed.

Configuration of the barge-in behavior. Barge-in instructs the API to return a detected utterance at a proper time while the client is playing back the response audio from a previous request. When the client sees the utterance, it should stop the playback and immediately get ready for receiving the responses for the current request. The barge-in handling requires the client to start streaming audio input as soon as it starts playing back the audio from the previous response. The playback is modeled into two phases: * No barge-in phase: which goes first and during which speech detection should not be carried out. * Barge-in phase: which follows the no barge-in phase and during which the API starts speech detection and may inform the client that an utterance has been detected. Note that no-speech event is not expected in this phase. The client provides this configuration in terms of the durations of those two phases. The durations are measured in terms of the audio length from the the start of the input audio. No-speech event is a response with END_OF_UTTERANCE without any transcript following up.

The request message for TestCases.BatchDeleteTestCases.

Metadata returned for the TestCases.BatchRunTestCases long running operation.

The request message for TestCases.BatchRunTestCases.

The response message for TestCases.BatchRunTestCases.

Hierarchical advanced settings for agent/flow/page/fulfillment/parameter. Settings exposed at lower level overrides the settings exposed at higher level. Overriding occurs at the sub-setting level. For example, the playback_interruption_settings at fulfillment level only overrides the playback_interruption_settings at the agent level, leaving other settings at the agent level unchanged. DTMF settings does not override each other. DTMF settings set at different levels define DTMF detections running in parallel. Hierarchy: Agent->Flow->Page->Fulfillment/Parameter.

Define behaviors for DTMF (dual tone multi frequency).

Define behaviors on logging.

Define behaviors of speech to text detection.

Represents the natural speech audio to be processed.

Configuration of the barge-in behavior. Barge-in instructs the API to return a detected utterance at a proper time while the client is playing back the response audio from a previous request. When the client sees the utterance, it should stop the playback and immediately get ready for receiving the responses for the current request. The barge-in handling requires the client to start streaming audio input as soon as it starts playing back the audio from the previous response. The playback is modeled into two phases: * No barge-in phase: which goes first and during which speech detection should not be carried out. * Barge-in phase: which follows the no barge-in phase and during which the API starts speech detection and may inform the client that an utterance has been detected. Note that no-speech event is not expected in this phase. The client provides this configuration in terms of the durations of those two phases. The durations are measured in terms of the audio length from the the start of the input audio. No-speech event is a response with END_OF_UTTERANCE without any transcript following up.

Metadata returned for the TestCases.BatchRunTestCases long running operation.

The response message for TestCases.BatchRunTestCases.

Represents a result from running a test case in an agent environment.

This message is used to hold all the Conversation Signals data, which will be converted to JSON and exported to BigQuery.

One interaction between a human and virtual agent. The human provides some input and the virtual agent provides a response.

The input from the human user.

The output from the virtual agent.

Metadata for CreateDocument operation.

Metadata associated with the long running operation for Versions.CreateVersion.

A data store connection. It represents a data store in Discovery Engine and the type of the contents it contains.

Metadata for DeleteDocument operation.

Metadata returned for the Environments.DeployFlow long running operation.

The response message for Environments.DeployFlow.

Represents the input for dtmf event.

Represents an environment for an agent. You can create multiple versions of your agent and publish them to separate environments. When you edit an agent, you are editing the draft agent. At any point, you can save the draft agent as an agent version, which is an immutable snapshot of your agent. When you save the draft agent, it is published to the default environment. When you create agent versions, you can publish them to custom environments. You can create a variety of custom environments for testing, development, production, etc.

The configuration for continuous tests.

Configuration for the version.

Configuration for webhooks.

An event handler specifies an event that can be handled during a session. When the specified event happens, the following actions are taken in order: * If there is a trigger_fulfillment associated with the event, it will be called. * If there is a target_page associated with the event, the session will transition into the specified page. * If there is a target_flow associated with the event, the session will transition into the specified flow.

Represents the event to trigger.

The response message for Agents.ExportAgent.

Metadata returned for the EntityTypes.ExportEntityTypes long running operation.

The response message for EntityTypes.ExportEntityTypes.

The response message for Flows.ExportFlow.

Metadata returned for the Intents.ExportIntents long running operation.

The response message for Intents.ExportIntents.

Metadata returned for the TestCases.ExportTestCases long running operation. This message currently has no fields.

The response message for TestCases.ExportTestCases.

A form is a data model that groups related parameters that can be collected from the user. The process in which the agent prompts the user and collects parameter values from the user is called form filling. A form can be added to a page. When form filling is done, the filled parameters will be written to the session.

Represents a form parameter.

Configuration for how the filling of a parameter should be handled.

A fulfillment can do one or more of the following actions at the same time:

• Generate rich message responses. * Set parameter values. * Call the webhook. Fulfillments can be called at various stages in the Page or Form lifecycle. For example, when a DetectIntentRequest drives a session to enter a new page, the page's entry fulfillment can add a static response to the QueryResult in the returning DetectIntentResponse, call the webhook (for example, to load user data from a database), or both.

A list of cascading if-else conditions. Cases are mutually exclusive. The first one with a matching condition is selected, all the rest ignored.

Each case has a Boolean condition. When it is evaluated to be True, the corresponding messages will be selected and evaluated recursively.

The list of messages or conditional cases to activate for this case.

Setting a parameter value.

Google Cloud Storage location for a Dialogflow operation that writes or exports objects (e.g. exported agent or transcripts) outside of Dialogflow.

Metadata in google::longrunning::Operation for Knowledge operations.

Metadata for ImportDocuments operation.

Response message for Documents.ImportDocuments.

Metadata returned for the EntityTypes.ImportEntityTypes long running operation.

The response message for EntityTypes.ImportEntityTypes.

Conflicting resources detected during the import process. Only filled when REPORT_CONFLICT is set in the request and there are conflicts in the display names.

The response message for Flows.ImportFlow.

Metadata returned for the Intents.ImportIntents long running operation.

The response message for Intents.ImportIntents.

Conflicting resources detected during the import process. Only filled when REPORT_CONFLICT is set in the request and there are conflicts in the display names.

Metadata returned for the TestCases.ImportTestCases long running operation.

The response message for TestCases.ImportTestCases.

Inline destination for a Dialogflow operation that writes or exports objects (e.g. intents) outside of Dialogflow.

Instructs the speech recognizer on how to process the audio content.

An intent represents a user's intent to interact with a conversational agent. You can provide information for the Dialogflow API to use to match user input to an intent by adding training phrases (i.e., examples of user input) to your intent.

Represents the intent to trigger programmatically rather than as a result of natural language processing.

Represents an intent parameter.

Represents an example that the agent is trained on to identify the intent.

Represents a part of a training phrase.

The Knowledge Connector settings for this page or flow. This includes information such as the attached Knowledge Bases, and the way to execute fulfillment.

A Dialogflow CX conversation (session) can be described and visualized as a state machine. The states of a CX session are represented by pages. For each flow, you define many pages, where your combined pages can handle a complete conversation on the topics the flow is designed for. At any given moment, exactly one page is the current page, the current page is considered active, and the flow associated with that page is considered active. Every flow has a special start page. When a flow initially becomes active, the start page page becomes the current page. For each conversational turn, the current page will either stay the same or transition to another page. You configure each page to collect information from the end-user that is relevant for the conversational state represented by the page. For more information, see the Page guide.

Represents page information communicated to and from the webhook.

Represents form information.

Represents parameter information.

Represents the query input. It can contain one of: 1. A conversational query in the form of text. 2. An intent query that specifies which intent to trigger. 3. Natural language speech audio to be processed. 4. An event to be triggered. 5. DTMF digits to invoke an intent and fill in parameter value. 6. The results of a tool executed by the client.

Metadata for ReloadDocument operation.

Represents a response message that can be returned by a conversational agent. Response messages are also used for output audio synthesis. The approach is as follows: * If at least one OutputAudioText response is present, then all OutputAudioText responses are linearly concatenated, and the result is used for output audio synthesis. * If the OutputAudioText responses are a mixture of text and SSML, then the concatenated result is treated as SSML; otherwise, the result is treated as either text or SSML as appropriate. The agent designer should ideally use either text or SSML consistently throughout the bot design. * Otherwise, all Text responses are linearly concatenated, and the result is used for output audio synthesis. This approach allows for more sophisticated user experience scenarios, where the text displayed to the user may differ from what is heard.

Indicates that the conversation succeeded, i.e., the bot handled the issue that the customer talked to it about. Dialogflow only uses this to determine which conversations should be counted as successful and doesn't process the metadata in this message in any way. Note that Dialogflow also considers conversations that get to the conversation end page as successful even if they don't return ConversationSuccess. You may set this, for example: * In the entry_fulfillment of a Page if entering the page indicates that the conversation succeeded. * In a webhook response when you determine that you handled the customer issue.

Indicates that interaction with the Dialogflow agent has ended. This message is generated by Dialogflow only and not supposed to be defined by the user.

Represents info card response. If the response contains generative knowledge prediction, Dialogflow will return a payload with Infobot Messenger compatible info card. Otherwise, the info card response is skipped.

Indicates that the conversation should be handed off to a live agent. Dialogflow only uses this to determine which conversations were handed off to a human agent for measurement purposes. What else to do with this signal is up to you and your handoff procedures. You may set this, for example: * In the entry_fulfillment of a Page if entering the page indicates something went extremely wrong in the conversation. * In a webhook response when you determine that the customer issue can only be handled by a human.

Represents an audio message that is composed of both segments synthesized from the Dialogflow agent prompts and ones hosted externally at the specified URIs. The external URIs are specified via play_audio. This message is generated by Dialogflow only and not supposed to be defined by the user.

Represents one segment of audio.

A text or ssml response that is preferentially used for TTS output audio synthesis, as described in the comment on the ResponseMessage message.

Specifies an audio clip to be played by the client as part of the response.

Represents the signal that telles the client to transfer the phone call connected to the agent to a third-party endpoint.

The text response message.

Metadata returned for the Environments.RunContinuousTest long running operation.

The response message for Environments.RunContinuousTest.

Metadata returned for the TestCases.RunTestCase long running operation. This message currently has no fields.

The response message for TestCases.RunTestCase.

Represents session information communicated to and from the webhook.

Represents a test case.

Error info for importing a test.

Represents a result from running a test case in an agent environment.

Represents configurations for a test case.

Error info for running a test.

The description of differences between original and replayed agent output.

Represents the natural language text to be processed.

A transition route specifies a intent that can be matched and/or a data condition that can be evaluated during a session. When a specified transition is matched, the following actions are taken in order: * If there is a trigger_fulfillment associated with the transition, it will be called. * If there is a target_page associated with the transition, the session will transition into the specified page. * If there is a target_flow associated with the transition, the session will transition into the specified flow.

Collection of all signals that were extracted for a single turn of the conversation.

Metadata for UpdateDocument operation.

Webhooks host the developer's business logic. During a session, webhooks allow the developer to use the data extracted by Dialogflow's natural language processing to generate dynamic responses, validate collected data, or trigger actions on the backend.

Represents configuration for a generic web service.

Represents configuration of OAuth client credential flow for 3rd party API authentication.

The request message for a webhook call. The request is sent as a JSON object and the field names will be presented in camel cases. You may see undocumented fields in an actual request. These fields are used internally by Dialogflow and should be ignored.

Represents fulfillment information communicated to the webhook.

Represents intent information communicated to the webhook.

Represents a value for an intent parameter.

Represents the result of sentiment analysis.

The response message for a webhook call.

Represents a fulfillment response to the user.

Represents configuration for a Service Directory service.

Boost specification to boost certain documents. A copy of google.cloud.discoveryengine.v1main.BoostSpec, field documentation is available at https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1alpha/BoostSpec

Boost applies to documents which match a condition.

Boost specifications for data stores.

The response message for TestCases.CalculateCoverage.

Changelogs represents a change made to a given agent.

The request message for Versions.CompareVersions.

The response message for Versions.CompareVersions.

Represents a result from running a test case in an agent environment.

This message is used to hold all the Conversation Signals data, which will be converted to JSON and exported to BigQuery.

One interaction between a human and virtual agent. The human provides some input and the virtual agent provides a response.

The input from the human user.

The output from the virtual agent.

Metadata for CreateDocument operation.

Metadata associated with the long running operation for Versions.CreateVersion.

A data store connection. It represents a data store in Discovery Engine and the type of the contents it contains.

Data store connection feature output signals. Might be only partially field if processing stop before the final answer. Reasons for this can be, but are not limited to: empty UCS search results, positive RAI check outcome, grounding failure, ...

Diagnostic info related to the answer generation model call.

Answer part with citation.

Snippet cited by the answer generation model.

Grounding signals.

Diagnostic info related to the rewriter model call.

Safety check results.

Search snippet details.

Metadata for DeleteDocument operation.

Metadata returned for the Environments.DeployFlow long running operation.

The request message for Environments.DeployFlow.

The response message for Environments.DeployFlow.

Represents a deployment in an environment. A deployment happens when a flow version configured to be active in the environment. You can configure running pre-deployment steps, e.g. running validation test cases, experiment auto-rollout, etc.

Result of the deployment.

The request to detect user's intent.

The message returned from the DetectIntent method.

Represents the input for dtmf event.

Entities are extracted from user input and represent parameters that are meaningful to your application. For example, a date range, a proper name such as a geographic location or landmark, and so on. Entities represent actionable data for your application. When you define an entity, you can also include synonyms that all map to that entity. For example, "soft drink", "soda", "pop", and so on. There are three types of entities: * System - entities that are defined by the Dialogflow API for common data types such as date, time, currency, and so on. A system entity is represented by the EntityType type. * Custom - entities that are defined by you that represent actionable data that is meaningful to your application. For example, you could define a pizza.sauce entity for red or white pizza sauce, a pizza.cheese entity for the different types of cheese on a pizza, a pizza.topping entity for different toppings, and so on. A custom entity is represented by the EntityType type. * User - entities that are built for an individual user such as favorites, preferences, playlists, and so on. A user entity is represented by the SessionEntityType type. For more information about entity types, see the Dialogflow documentation.

An entity entry for an associated entity type.

An excluded entity phrase that should not be matched.

Represents an environment for an agent. You can create multiple versions of your agent and publish them to separate environments. When you edit an agent, you are editing the draft agent. At any point, you can save the draft agent as an agent version, which is an immutable snapshot of your agent. When you save the draft agent, it is published to the default environment. When you create agent versions, you can publish them to custom environments. You can create a variety of custom environments for testing, development, production, etc.

The configuration for continuous tests.

Configuration for the version.

Configuration for webhooks.

An event handler specifies an event that can be handled during a session. When the specified event happens, the following actions are taken in order: * If there is a trigger_fulfillment associated with the event, it will be called. * If there is a target_page associated with the event, the session will transition into the specified page. * If there is a target_flow associated with the event, the session will transition into the specified flow.

Represents the event to trigger.

Represents an experiment in an environment.

Definition of the experiment.

The inference result which includes an objective metric to optimize and the confidence interval.

A confidence interval is a range of possible values for the experiment objective you are trying to measure.

Metric and corresponding confidence intervals.

Version variant and associated metrics.

The request message for Agents.ExportAgent.

Settings for exporting to a git branch.

The response message for Agents.ExportAgent.

Metadata returned for the EntityTypes.ExportEntityTypes long running operation.

The request message for EntityTypes.ExportEntityTypes.

The response message for EntityTypes.ExportEntityTypes.

The request message for Flows.ExportFlow.

The response message for Flows.ExportFlow.

Metadata returned for the Intents.ExportIntents long running operation.

The request message for Intents.ExportIntents.

The response message for Intents.ExportIntents.

Metadata returned for the TestCases.ExportTestCases long running operation. This message currently has no fields.

The request message for TestCases.ExportTestCases.

The response message for TestCases.ExportTestCases.

Filter specifications for data stores.

Flows represents the conversation flows when you build your chatbot agent. A flow consists of many pages connected by the transition routes. Conversations always start with the built-in Start Flow (with an all-0 ID). Transition routes can direct the conversation session from the current flow (parent flow) to another flow (sub flow). When the sub flow is finished, Dialogflow will bring the session back to the parent flow, where the sub flow is started. Usually, when a transition route is followed by a matched intent, the intent will be "consumed". This means the intent won't activate more transition routes. However, when the followed transition route moves the conversation session into a different flow, the matched intent can be carried over and to be consumed in the target flow.

The flow import strategy used for resource conflict resolution associated with an ImportFlowRequest.

Settings for multi-lingual agents.

The response message for Flows.GetFlowValidationResult.

A form is a data model that groups related parameters that can be collected from the user. The process in which the agent prompts the user and collects parameter values from the user is called form filling. A form can be added to a page. When form filling is done, the filled parameters will be written to the session.

Represents a form parameter.

Configuration for how the filling of a parameter should be handled.

Request of FulfillIntent

Response of FulfillIntent

A fulfillment can do one or more of the following actions at the same time:

• Generate rich message responses. * Set parameter values. * Call the webhook. Fulfillments can be called at various stages in the Page or Form lifecycle. For example, when a DetectIntentRequest drives a session to enter a new page, the page's entry fulfillment can add a static response to the QueryResult in the returning DetectIntentResponse, call the webhook (for example, to load user data from a database), or both.

A list of cascading if-else conditions. Cases are mutually exclusive. The first one with a matching condition is selected, all the rest ignored.

Each case has a Boolean condition. When it is evaluated to be True, the corresponding messages will be selected and evaluated recursively.

The list of messages or conditional cases to activate for this case.

Setting a parameter value.

Google Cloud Storage location for a Dialogflow operation that writes or exports objects (e.g. exported agent or transcripts) outside of Dialogflow.

Settings for Generative AI.

Settings for Generative Fallback.

Prompt template.

Settings for knowledge connector. These parameters are used for LLM prompt like "You are . You are a helpful and verbose at , . Your task is to help humans on ".

Generators contain prompt to be sent to the LLM model to generate text. The prompt can contain parameters which will be resolved before calling the model. It can optionally contain banned phrases to ensure the model responses are safe.

Represents a custom placeholder in the prompt text.

Metadata in google::longrunning::Operation for Knowledge operations.

Metadata for ImportDocuments operation.

Response message for Documents.ImportDocuments.

Metadata returned for the EntityTypes.ImportEntityTypes long running operation.

The request message for EntityTypes.ImportEntityTypes.

The response message for EntityTypes.ImportEntityTypes.

Conflicting resources detected during the import process. Only filled when REPORT_CONFLICT is set in the request and there are conflicts in the display names.

The request message for Flows.ImportFlow.

The response message for Flows.ImportFlow.

Metadata returned for the Intents.ImportIntents long running operation.

The request message for Intents.ImportIntents.

The response message for Intents.ImportIntents.

Conflicting resources detected during the import process. Only filled when REPORT_CONFLICT is set in the request and there are conflicts in the display names.

Metadata returned for the TestCases.ImportTestCases long running operation.

The request message for TestCases.ImportTestCases.

The response message for TestCases.ImportTestCases.

Inline destination for a Dialogflow operation that writes or exports objects (e.g. intents) outside of Dialogflow.

Inline source for a Dialogflow operation that reads or imports objects (e.g. intents) into Dialogflow.

Instructs the speech recognizer on how to process the audio content.

An intent represents a user's intent to interact with a conversational agent. You can provide information for the Dialogflow API to use to match user input to an intent by adding training phrases (i.e., examples of user input) to your intent.

Intent coverage represents the percentage of all possible intents in the agent that are triggered in any of a parent's test cases.

The agent's intent.

Represents the intent to trigger programmatically rather than as a result of natural language processing.

Represents an intent parameter.

Represents an example that the agent is trained on to identify the intent.

Represents a part of a training phrase.

The Knowledge Connector settings for this page or flow. This includes information such as the attached Knowledge Bases, and the way to execute fulfillment.

The response message for Agents.ListAgents.

The response message for Changelogs.ListChangelogs.

The response message for Environments.ListTestCaseResults.

The response message for Deployments.ListDeployments.

The response message for EntityTypes.ListEntityTypes.

The response message for Environments.ListEnvironments.

The response message for Experiments.ListExperiments.

The response message for Flows.ListFlows.

The response message for Generators.ListGenerators.

The response message for Intents.ListIntents.

The response message for Pages.ListPages.

The response message for SecuritySettings.ListSecuritySettings.

The response message for SessionEntityTypes.ListSessionEntityTypes.

The response message for TestCases.ListTestCaseResults.

The response message for TestCases.ListTestCases.

The response message for TransitionRouteGroups.ListTransitionRouteGroups.

The response message for Versions.ListVersions.

The response message for Webhooks.ListWebhooks.

The request message for Versions.LoadVersion.

The response message for Environments.LookupEnvironmentHistory.

Represents one match result of MatchIntent.

Request of MatchIntent.

Response of MatchIntent.

Settings related to NLU.

Instructs the speech synthesizer how to generate the output audio content.

A Dialogflow CX conversation (session) can be described and visualized as a state machine. The states of a CX session are represented by pages. For each flow, you define many pages, where your combined pages can handle a complete conversation on the topics the flow is designed for. At any given moment, exactly one page is the current page, the current page is considered active, and the flow associated with that page is considered active. Every flow has a special start page. When a flow initially becomes active, the start page page becomes the current page. For each conversational turn, the current page will either stay the same or transition to another page. You configure each page to collect information from the end-user that is relevant for the conversational state represented by the page. For more information, see the Page guide.

Represents page information communicated to and from the webhook.

Represents form information.

Represents parameter information.

Text input which can be used for prompt or banned phrases.

Represents the query input. It can contain one of: 1. A conversational query in the form of text. 2. An intent query that specifies which intent to trigger. 3. Natural language speech audio to be processed. 4. An event to be triggered. 5. DTMF digits to invoke an intent and fill in parameter value. 6. The results of a tool executed by the client.

Represents the parameters of a conversational query.

Represents the result of a conversational query.

Metadata for ReloadDocument operation.

Resource name and display name.

Represents a response message that can be returned by a conversational agent. Response messages are also used for output audio synthesis. The approach is as follows: * If at least one OutputAudioText response is present, then all OutputAudioText responses are linearly concatenated, and the result is used for output audio synthesis. * If the OutputAudioText responses are a mixture of text and SSML, then the concatenated result is treated as SSML; otherwise, the result is treated as either text or SSML as appropriate. The agent designer should ideally use either text or SSML consistently throughout the bot design. * Otherwise, all Text responses are linearly concatenated, and the result is used for output audio synthesis. This approach allows for more sophisticated user experience scenarios, where the text displayed to the user may differ from what is heard.

Indicates that the conversation succeeded, i.e., the bot handled the issue that the customer talked to it about. Dialogflow only uses this to determine which conversations should be counted as successful and doesn't process the metadata in this message in any way. Note that Dialogflow also considers conversations that get to the conversation end page as successful even if they don't return ConversationSuccess. You may set this, for example: * In the entry_fulfillment of a Page if entering the page indicates that the conversation succeeded. * In a webhook response when you determine that you handled the customer issue.

Indicates that interaction with the Dialogflow agent has ended. This message is generated by Dialogflow only and not supposed to be defined by the user.

Represents info card response. If the response contains generative knowledge prediction, Dialogflow will return a payload with Infobot Messenger compatible info card. Otherwise, the info card response is skipped.

Indicates that the conversation should be handed off to a live agent. Dialogflow only uses this to determine which conversations were handed off to a human agent for measurement purposes. What else to do with this signal is up to you and your handoff procedures. You may set this, for example: * In the entry_fulfillment of a Page if entering the page indicates something went extremely wrong in the conversation. * In a webhook response when you determine that the customer issue can only be handled by a human.

Represents an audio message that is composed of both segments synthesized from the Dialogflow agent prompts and ones hosted externally at the specified URIs. The external URIs are specified via play_audio. This message is generated by Dialogflow only and not supposed to be defined by the user.

Represents one segment of audio.

A text or ssml response that is preferentially used for TTS output audio synthesis, as described in the comment on the ResponseMessage message.

Specifies an audio clip to be played by the client as part of the response.

Represents the signal that telles the client to transfer the phone call connected to the agent to a third-party endpoint.

The text response message.

The request message for Agents.RestoreAgent.

Settings for restoring from a git branch

The configuration for auto rollout.

A single rollout step with specified traffic allocation.

State of the auto-rollout process.

Metadata returned for the Environments.RunContinuousTest long running operation.

The request message for Environments.RunContinuousTest.

The response message for Environments.RunContinuousTest.

Metadata returned for the TestCases.RunTestCase long running operation. This message currently has no fields.

The request message for TestCases.RunTestCase.

The response message for TestCases.RunTestCase.

Settings for Generative Safety.

Text input which can be used for prompt or banned phrases.

Search configuration for UCS search queries.

Represents the settings related to security issues, such as data redaction and data retention. It may take hours for updates on the settings to propagate to all the related components and take effect.

Settings for exporting audio.

Settings for exporting conversations to Insights.

The result of sentiment analysis. Sentiment analysis inspects user input and identifies the prevailing subjective opinion, especially to determine a user's attitude as positive, negative, or neutral.

Session entity types are referred to as User entity types and are entities that are built for an individual user such as favorites, preferences, playlists, and so on. You can redefine a session entity type at the session level to extend or replace a custom entity type at the user session level (we refer to the entity types defined at the agent level as "custom entity types"). Note: session entity types apply to all queries, regardless of the language. For more information about entity types, see the Dialogflow documentation.

Represents session information communicated to and from the webhook.

Settings related to speech recognition.

The request message for Experiments.StartExperiment.

The request message for Experiments.StopExperiment.

The request to set the feedback for a bot answer.

Configuration of how speech should be synthesized.

Represents a test case.

Error info for importing a test.

Represents a result from running a test case in an agent environment.

Represents configurations for a test case.

Error info for running a test.

The description of differences between original and replayed agent output.

Represents the natural language text to be processed.

Settings related to speech synthesizing.

The request message for Flows.TrainFlow.

Transition coverage represents the percentage of all possible page transitions (page-level transition routes and event handlers, excluding transition route groups) present within any of a parent's test cases.

A transition in a page.

The source or target of a transition.

A transition route specifies a intent that can be matched and/or a data condition that can be evaluated during a session. When a specified transition is matched, the following actions are taken in order: * If there is a trigger_fulfillment associated with the transition, it will be called. * If there is a target_page associated with the transition, the session will transition into the specified page. * If there is a target_flow associated with the transition, the session will transition into the specified flow.

A TransitionRouteGroup represents a group of TransitionRoutes to be used by a Page.

Transition route group coverage represents the percentage of all possible transition routes present within any of a parent's test cases. The results are grouped by the transition route group.

Coverage result message for one transition route group.

A transition coverage in a transition route group.

Collection of all signals that were extracted for a single turn of the conversation.

Metadata for UpdateDocument operation.

The request message for Agents.ValidateAgent.

The request message for Flows.ValidateFlow.

Agent/flow validation message.

The history of variants update.

Represents a version of a flow.

A list of flow version variants.

A single flow version with specified traffic allocation.

Description of which voice to use for speech synthesis.

Webhooks host the developer's business logic. During a session, webhooks allow the developer to use the data extracted by Dialogflow's natural language processing to generate dynamic responses, validate collected data, or trigger actions on the backend.

Represents configuration for a generic web service.

Represents configuration of OAuth client credential flow for 3rd party API authentication.

The request message for a webhook call. The request is sent as a JSON object and the field names will be presented in camel cases. You may see undocumented fields in an actual request. These fields are used internally by Dialogflow and should be ignored.

Represents fulfillment information communicated to the webhook.

Represents intent information communicated to the webhook.

Represents a value for an intent parameter.

Represents the result of sentiment analysis.

The response message for a webhook call.

Represents a fulfillment response to the user.

Represents configuration for a Service Directory service.

Represents a part of a message possibly annotated with an entity. The part can be an entity or purely a part of the message between two entities or message start/end.

Represents article answer.

Metadata for article suggestion models.

The response message for EntityTypes.BatchUpdateEntityTypes.

The response message for Intents.BatchUpdateIntents.

Represents a part of a message possibly annotated with an entity. The part can be an entity or purely a part of the message between two entities or message start/end.

Represents article answer.

The response message for EntityTypes.BatchUpdateEntityTypes.

The response message for Intents.BatchUpdateIntents.

Metadata for a ConversationProfile.ClearSuggestionFeatureConfig operation.

Dialogflow contexts are similar to natural language context. If a person says to you "they are orange", you need context in order to understand what "they" is referring to. Similarly, for Dialogflow to handle an end-user expression like that, it needs to be provided with context in order to correctly match an intent. Using contexts, you can control the flow of a conversation. You can configure contexts for an intent by setting input and output contexts, which are identified by string names. When an intent is matched, any configured output contexts for that intent become active. While any contexts are active, Dialogflow is more likely to match intents that are configured with input contexts that correspond to the currently active contexts. For more information about context, see the Contexts guide.

Represents a notification sent to Pub/Sub subscribers for conversation lifecycle events.

Represents a Dialogflow assist answer.

Each intent parameter has a type, called the entity type, which dictates exactly how data from an end-user expression is extracted. Dialogflow provides predefined system entities that can match many common types of data. For example, there are system entities for matching dates, times, colors, email addresses, and so on. You can also create your own custom entities for matching custom data. For example, you could define a vegetable entity that can match the types of vegetables available for purchase with a grocery store agent. For more information, see the Entity guide.

An entity entry for an associated entity type.

Events allow for matching intents by event name instead of the natural language input. For instance, input `` can trigger a personalized welcome response. The parameter name may be used by the agent in the response: `"Hello #welcome_event.name! What can I do for you today?"`.

The response message for Agents.ExportAgent.

Metadata related to the Export Data Operations (e.g. ExportDocument).

Represents answer from "frequently asked questions".

Google Cloud Storage location for the output.

Output only. Represents a notification sent to Pub/Sub subscribers for agent assistant events in a specific conversation.

Response message for Documents.ImportDocuments.

An intent categorizes an end-user's intention for one conversation turn. For each agent, you define many intents, where your combined intents can handle a complete conversation. When an end-user writes or says something, referred to as an end-user expression or end-user input, Dialogflow matches the end-user input to the best intent in your agent. Matching an intent is also known as intent classification. For more information, see the intent guide.

Represents a single followup intent in the chain.

Corresponds to the Response field in the Dialogflow console.

The basic card message. Useful for displaying information.

The button object that appears at the bottom of a card.

Opens the given URI.

Browse Carousel Card for Actions on Google. https://developers.google.com/actions/assistant/responses#browsing_carousel

Browsing carousel tile

Actions on Google action to open a given url.

The card response message.

Optional. Contains information about a button.

The card for presenting a carousel of options to select from.

An item in the carousel.

Column properties for TableCard.

The image response message.

The suggestion chip message that allows the user to jump out to the app or website associated with this agent.

The card for presenting a list of options to select from.

An item in the list.

The media content card for Actions on Google.

Response media object for media content card.

The quick replies response message.

Rich Business Messaging (RBM) Card content

Rich Business Messaging (RBM) Media displayed in Cards The following media-types are currently supported: Image Types * image/jpeg * image/jpg' * image/gif * image/png Video Types * video/h263 * video/m4v * video/mp4 * video/mpeg * video/mpeg4 * video/webm

Carousel Rich Business Messaging (RBM) rich card. Rich cards allow you to respond to users with more vivid content, e.g. with media and suggestions. If you want to show a single card with more control over the layout, please use RbmStandaloneCard instead.

Standalone Rich Business Messaging (RBM) rich card. Rich cards allow you to respond to users with more vivid content, e.g. with media and suggestions. You can group multiple rich cards into one using RbmCarouselCard but carousel cards will give you less control over the card layout.

Rich Business Messaging (RBM) suggested client-side action that the user can choose from the card.

Opens the user's default dialer app with the specified phone number but does not dial automatically.

Opens the user's default web browser app to the specified uri If the user has an app installed that is registered as the default handler for the URL, then this app will be opened instead, and its icon will be used in the suggested action UI.

Opens the device's location chooser so the user can pick a location to send back to the agent.

Rich Business Messaging (RBM) suggested reply that the user can click instead of typing in their own response.

Rich Business Messaging (RBM) suggestion. Suggestions allow user to easily select/click a predefined response or perform an action (like opening a web uri).

Rich Business Messaging (RBM) text response with suggestions.

Additional info about the select item for when it is triggered in a dialog.

The simple response message containing speech or text.

The collection of simple response candidates. This message in QueryResult.fulfillment_messages and WebhookResponse.fulfillment_messages should contain only one SimpleResponse.

The suggestion chip message that the user can tap to quickly post a reply to the conversation.

The collection of suggestions.

Table card for Actions on Google.

Cell of TableCardRow.

Row of TableCard.

Plays audio from a file in Telephony Gateway.

Synthesizes speech and plays back the synthesized audio to the caller in Telephony Gateway. Telephony Gateway takes the synthesizer settings from DetectIntentResponse.output_audio_config which can either be set at request-level or can come from the agent-level synthesizer config.

Transfers the call in Telephony Gateway.

The text response message.

Represents intent parameters.

Represents an intent suggestion.

Represents an example that the agent is trained on.

Represents a part of a training phrase.

Represents the result of querying a Knowledge base.

An answer from Knowledge Connector.

Metadata in google::longrunning::Operation for Knowledge operations.

Represents a message posted into a conversation.

Represents the result of annotation for the message.

Represents the contents of the original request that was passed to the [Streaming]DetectIntent call.

Represents the result of conversational query or event processing.

The sentiment, such as positive/negative feeling or association, for a unit of analysis, such as the query text. See: https://cloud.google.com/natural-language/docs/basics#interpreting_sentiment_analysis_values for how to interpret the result.

The result of sentiment analysis. Sentiment analysis inspects user input and identifies the prevailing subjective opinion, especially to determine a user's attitude as positive, negative, or neutral. For Participants.DetectIntent, it needs to be configured in DetectIntentRequest.query_params. For Participants.StreamingDetectIntent, it needs to be configured in StreamingDetectIntentRequest.query_params. And for Participants.AnalyzeContent and Participants.StreamingAnalyzeContent, it needs to be configured in ConversationProfile.human_agent_assistant_config

A session represents a conversation between a Dialogflow agent and an end-user. You can create special entities, called session entities, during a session. Session entities can extend or replace custom entity types and only exist during the session that they were created for. All session data, including session entities, is stored by Dialogflow for 20 minutes. For more information, see the session entity guide.

Metadata for a ConversationProfile.SetSuggestionFeatureConfig operation.

Represents a smart reply answer.

The response message for Participants.SuggestArticles.

The response message for Participants.SuggestDialogflowAssists.

The request message for Participants.SuggestFaqAnswers.

One response of different type of suggestion response which is used in the response of Participants.AnalyzeContent and Participants.AnalyzeContent, as well as HumanAgentAssistantEvent.

The response message for Participants.SuggestSmartReplies.

The request message for a webhook call.

The response message for a webhook call. This response is validated by the Dialogflow server. If validation fails, an error will be returned in the QueryResult.diagnostic_info field. Setting JSON fields to an empty value with the wrong type is a common error. To avoid this error: - Use "" for empty strings - Use {} or null for empty objects - Use [] or null for empty arrays For more information, see the Protocol Buffers Language Guide.

Metadata for a ConversationProfile.ClearSuggestionFeatureConfig operation.

Dialogflow contexts are similar to natural language context. If a person says to you "they are orange", you need context in order to understand what "they" is referring to. Similarly, for Dialogflow to handle an end-user expression like that, it needs to be provided with context in order to correctly match an intent. Using contexts, you can control the flow of a conversation. You can configure contexts for an intent by setting input and output contexts, which are identified by string names. When an intent is matched, any configured output contexts for that intent become active. While any contexts are active, Dialogflow is more likely to match intents that are configured with input contexts that correspond to the currently active contexts. For more information about context, see the Contexts guide.

Represents a notification sent to Pub/Sub subscribers for conversation lifecycle events.

Represents a conversation model.

Metadata for ConversationDatasets.

Metadata for a ConversationModels.CreateConversationModelEvaluation operation.

Metadata for a ConversationModels.CreateConversationModel operation.

Metadata for ConversationDatasets.

Metadata for a ConversationModels.DeleteConversationModel operation.

Metadata for a ConversationModels.DeployConversationModel operation.

Each intent parameter has a type, called the entity type, which dictates exactly how data from an end-user expression is extracted. Dialogflow provides predefined system entities that can match many common types of data. For example, there are system entities for matching dates, times, colors, email addresses, and so on. You can also create your own custom entities for matching custom data. For example, you could define a vegetable entity that can match the types of vegetables available for purchase with a grocery store agent. For more information, see the Entity guide.

An entity entry for an associated entity type.

Events allow for matching intents by event name instead of the natural language input. For instance, input `` can trigger a personalized welcome response. The parameter name may be used by the agent in the response: `"Hello #welcome_event.name! What can I do for you today?"`.

The response message for Agents.ExportAgent.

Metadata related to the Export Data Operations (e.g. ExportDocument).

Represents answer from "frequently asked questions".

Google Cloud Storage location for the output.

Represents a notification sent to Cloud Pub/Sub subscribers for human agent assistant events in a specific conversation.

Metadata for a ConversationDatasets.ImportConversationData operation.

Response used for ConversationDatasets.ImportConversationData long running operation.

Response message for Documents.ImportDocuments.

InputDataset used to create model or do evaluation. NextID:5

An intent categorizes an end-user's intention for one conversation turn. For each agent, you define many intents, where your combined intents can handle a complete conversation. When an end-user writes or says something, referred to as an end-user expression or end-user input, Dialogflow matches the end-user input to the best intent in your agent. Matching an intent is also known as intent classification. For more information, see the intent guide.

Represents a single followup intent in the chain.

A rich response message. Corresponds to the intent Response field in the Dialogflow console. For more information, see Rich response messages.

The basic card message. Useful for displaying information.

The button object that appears at the bottom of a card.

Opens the given URI.

Browse Carousel Card for Actions on Google. https://developers.google.com/actions/assistant/responses#browsing_carousel

Browsing carousel tile

Actions on Google action to open a given url.

The card response message.

Contains information about a button.

The card for presenting a carousel of options to select from.

An item in the carousel.

Column properties for TableCard.

The image response message.

The suggestion chip message that allows the user to jump out to the app or website associated with this agent.

The card for presenting a list of options to select from.

An item in the list.

The media content card for Actions on Google.

Response media object for media content card.

The quick replies response message.

Additional info about the select item for when it is triggered in a dialog.

The simple response message containing speech or text.

The collection of simple response candidates. This message in QueryResult.fulfillment_messages and WebhookResponse.fulfillment_messages should contain only one SimpleResponse.

The suggestion chip message that the user can tap to quickly post a reply to the conversation.

The collection of suggestions.

Table card for Actions on Google.

Cell of TableCardRow.

Row of TableCard.

The text response message.

Represents intent parameters.

Represents an example that the agent is trained on.

Represents a part of a training phrase.

Metadata in google::longrunning::Operation for Knowledge operations.

Represents a message posted into a conversation.

Represents the result of annotation for the message.

Represents the contents of the original request that was passed to the [Streaming]DetectIntent call.

Represents the result of conversational query or event processing.

The sentiment, such as positive/negative feeling or association, for a unit of analysis, such as the query text. See: https://cloud.google.com/natural-language/docs/basics#interpreting_sentiment_analysis_values for how to interpret the result.

The result of sentiment analysis. Sentiment analysis inspects user input and identifies the prevailing subjective opinion, especially to determine a user's attitude as positive, negative, or neutral. For Participants.DetectIntent, it needs to be configured in DetectIntentRequest.query_params. For Participants.StreamingDetectIntent, it needs to be configured in StreamingDetectIntentRequest.query_params. And for Participants.AnalyzeContent and Participants.StreamingAnalyzeContent, it needs to be configured in ConversationProfile.human_agent_assistant_config

A session represents a conversation between a Dialogflow agent and an end-user. You can create special entities, called session entities, during a session. Session entities can extend or replace custom entity types and only exist during the session that they were created for. All session data, including session entities, is stored by Dialogflow for 20 minutes. For more information, see the session entity guide.

Metadata for a ConversationProfile.SetSuggestionFeatureConfig operation.

Represents a smart reply answer.

Metadata for smart reply models.

The response message for Participants.SuggestArticles.

The request message for Participants.SuggestFaqAnswers.

One response of different type of suggestion response which is used in the response of Participants.AnalyzeContent and Participants.AnalyzeContent, as well as HumanAgentAssistantEvent.

The response message for Participants.SuggestSmartReplies.

Metadata for a ConversationModels.UndeployConversationModel operation.

The request message for a webhook call.

The response message for a webhook call. This response is validated by the Dialogflow server. If validation fails, an error will be returned in the QueryResult.diagnostic_info field. Setting JSON fields to an empty value with the wrong type is a common error. To avoid this error: - Use "" for empty strings - Use {} or null for empty objects - Use [] or null for empty arrays For more information, see the Protocol Buffers Language Guide.

This message is used to hold all the Conversation Signals data, which will be converted to JSON and exported to BigQuery.

Metadata for CreateDocument operation.

Metadata for DeleteDocument operation.

Metadata in google::longrunning::Operation for Knowledge operations.

Metadata for ImportDocuments operation.

Response message for Documents.ImportDocuments.

Metadata for ReloadDocument operation.

Collection of all signals that were extracted for a single turn of the conversation.

Metadata for UpdateDocument operation.

The response message for Locations.ListLocations.

A resource that represents a Google Cloud location.

The response message for Operations.ListOperations.

This resource represents a long-running operation that is the result of a network API call.

A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }

The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC. Each Status message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide.

An object that represents a latitude/longitude pair. This is expressed as a pair of doubles to represent degrees latitude and degrees longitude. Unless specified otherwise, this object must conform to the WGS84 standard. Values must be within normalized ranges.

Additional options for Dialogflow#projectsLocationsAgentsChangelogsList.

Additional options for Dialogflow#projectsLocationsAgentsEntityTypesCreate.

Additional options for Dialogflow#projectsLocationsAgentsEntityTypesDelete.

Additional options for Dialogflow#projectsLocationsAgentsEntityTypesGet.

Additional options for Dialogflow#projectsLocationsAgentsEntityTypesList.

Additional options for Dialogflow#projectsLocationsAgentsEntityTypesPatch.

Additional options for Dialogflow#projectsLocationsAgentsEnvironmentsContinuousTestResultsList.

Additional options for Dialogflow#projectsLocationsAgentsEnvironmentsDeploymentsList.

Additional options for Dialogflow#projectsLocationsAgentsEnvironmentsExperimentsList.

Additional options for Dialogflow#projectsLocationsAgentsEnvironmentsExperimentsPatch.

Additional options for Dialogflow#projectsLocationsAgentsEnvironmentsList.

Additional options for Dialogflow#projectsLocationsAgentsEnvironmentsLookupEnvironmentHistory.

Additional options for Dialogflow#projectsLocationsAgentsEnvironmentsPatch.

Additional options for Dialogflow#projectsLocationsAgentsEnvironmentsSessionsEntityTypesList.

Additional options for Dialogflow#projectsLocationsAgentsEnvironmentsSessionsEntityTypesPatch.

Additional options for Dialogflow#projectsLocationsAgentsFlowsCreate.

Additional options for Dialogflow#projectsLocationsAgentsFlowsDelete.

Additional options for Dialogflow#projectsLocationsAgentsFlowsGet.

Additional options for Dialogflow#projectsLocationsAgentsFlowsGetValidationResult.

Additional options for Dialogflow#projectsLocationsAgentsFlowsList.

Additional options for Dialogflow#projectsLocationsAgentsFlowsPagesCreate.

Additional options for Dialogflow#projectsLocationsAgentsFlowsPagesDelete.

Additional options for Dialogflow#projectsLocationsAgentsFlowsPagesGet.

Additional options for Dialogflow#projectsLocationsAgentsFlowsPagesList.

Additional options for Dialogflow#projectsLocationsAgentsFlowsPagesPatch.

Additional options for Dialogflow#projectsLocationsAgentsFlowsPatch.

Additional options for Dialogflow#projectsLocationsAgentsFlowsTransitionRouteGroupsCreate.

Additional options for Dialogflow#projectsLocationsAgentsFlowsTransitionRouteGroupsDelete.

Additional options for Dialogflow#projectsLocationsAgentsFlowsTransitionRouteGroupsGet.

Additional options for Dialogflow#projectsLocationsAgentsFlowsTransitionRouteGroupsList.

Additional options for Dialogflow#projectsLocationsAgentsFlowsTransitionRouteGroupsPatch.

Additional options for Dialogflow#projectsLocationsAgentsFlowsVersionsList.

Additional options for Dialogflow#projectsLocationsAgentsFlowsVersionsPatch.

Additional options for Dialogflow#projectsLocationsAgentsGeneratorsCreate.

Additional options for Dialogflow#projectsLocationsAgentsGeneratorsDelete.

Additional options for Dialogflow#projectsLocationsAgentsGeneratorsGet.

Additional options for Dialogflow#projectsLocationsAgentsGeneratorsList.

Additional options for Dialogflow#projectsLocationsAgentsGeneratorsPatch.

Additional options for Dialogflow#projectsLocationsAgentsGetGenerativeSettings.

Additional options for Dialogflow#projectsLocationsAgentsGetValidationResult.

Additional options for Dialogflow#projectsLocationsAgentsIntentsCreate.

Additional options for Dialogflow#projectsLocationsAgentsIntentsGet.

Additional options for Dialogflow#projectsLocationsAgentsIntentsList.

Additional options for Dialogflow#projectsLocationsAgentsIntentsPatch.

Additional options for Dialogflow#projectsLocationsAgentsList.

Additional options for Dialogflow#projectsLocationsAgentsPatch.

Additional options for Dialogflow#projectsLocationsAgentsSessionsEntityTypesList.

Additional options for Dialogflow#projectsLocationsAgentsSessionsEntityTypesPatch.

Additional options for Dialogflow#projectsLocationsAgentsTestCasesCalculateCoverage.

Additional options for Dialogflow#projectsLocationsAgentsTestCasesList.

Additional options for Dialogflow#projectsLocationsAgentsTestCasesPatch.

Additional options for Dialogflow#projectsLocationsAgentsTestCasesResultsList.

Additional options for Dialogflow#projectsLocationsAgentsTransitionRouteGroupsCreate.

Additional options for Dialogflow#projectsLocationsAgentsTransitionRouteGroupsDelete.

Additional options for Dialogflow#projectsLocationsAgentsTransitionRouteGroupsGet.

Additional options for Dialogflow#projectsLocationsAgentsTransitionRouteGroupsList.

Additional options for Dialogflow#projectsLocationsAgentsTransitionRouteGroupsPatch.

Additional options for Dialogflow#projectsLocationsAgentsUpdateGenerativeSettings.

Additional options for Dialogflow#projectsLocationsAgentsWebhooksDelete.

Additional options for Dialogflow#projectsLocationsAgentsWebhooksList.

Additional options for Dialogflow#projectsLocationsAgentsWebhooksPatch.

Additional options for Dialogflow#projectsLocationsList.

Additional options for Dialogflow#projectsLocationsOperationsList.

Additional options for Dialogflow#projectsLocationsSecuritySettingsList.

Additional options for Dialogflow#projectsLocationsSecuritySettingsPatch.

Additional options for Dialogflow#projectsOperationsList.