A Dialogflow agent is a virtual agent that handles conversations with your end-users. It is a natural language understanding module that understands the nuances of human language. Dialogflow translates end-user text or audio during a conversation to structured data that your apps and services can understand. You design and build a Dialogflow agent to handle the types of conversations required for your system. For more information about agents, see the Agent guide.
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.
Answer records are records to manage answer history and feedbacks for Dialogflow. Currently, answer record includes: - human agent assistant article suggestion - human agent assistant faq article It doesn’t include: - DetectIntent intent matching - DetectIntent knowledge Answer records are not related to the conversation history in the Dialogflow Console. A Record is generated even when the end-user disables conversation history in the console. Records are created when there’s a human agent assistant suggestion generated. A typical workflow for customers provide feedback to an answer is: 1. For human agent assistant, customers get suggestion via ListSuggestions API. Together with the answers, AnswerRecord.name are returned to the customers. 2. The customer uses the AnswerRecord.name to call the UpdateAnswerRecord method to send feedback about a specific answer that they believe is wrong.
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 conversation. A conversation is an interaction between an agent, including live agents and Dialogflow agents, and a support customer. Conversations can include phone calls and text-based chat sessions.
Represents a conversation dataset that a user imports raw data into. The data inside ConversationDataset can not be changed after ImportConversationData finishes (and calling ImportConversationData on a dataset that already has data is not allowed).
A knowledge document to be used by a KnowledgeBase. For more information, see the knowledge base guide. Note: The projects.agent.knowledgeBases.documents resource is deprecated; only use projects.knowledgeBases.documents.
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.
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. For more information, see the versions and environments guide.
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?".
By default, your agent responds to a matched intent with a static response. As an alternative, you can provide a more dynamic response by using fulfillment. When you enable fulfillment for an intent, Dialogflow responds to that intent by calling a service that you define. For example, if an end-user wants to schedule a haircut on Friday, your service can check your database and respond to the end-user with availability information for Friday. For more information, see the fulfillment guide.
Represents configuration for a generic web service. Dialogflow supports two mechanisms for authentications: - Basic authentication with username and password. - Authentication with additional authentication headers. More information could be found at: https://cloud.google.com/dialogflow/docs/fulfillment-configure.
Custom sections to return when requesting a summary of a conversation. This is only supported when baseline_model_version == ‘2.0’. Supported features: CONVERSATION_SUMMARIZATION, CONVERSATION_SUMMARIZATION_VOICE.
Defines the hand off to a live agent, typically on which external agent service provider to connect to a conversation. Currently, this feature is not general available, please contact Google to get access.
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.
The collection of simple response candidates. This message in QueryResult.fulfillment_messages and WebhookResponse.fulfillment_messages should contain only one SimpleResponse.
A knowledge base represents a collection of knowledge documents that you provide to Dialogflow. Your knowledge documents contain information that may be useful during conversations with end-users. Some Dialogflow features use knowledge bases when looking for a response to an end-user input. For more information, see the knowledge base guide. Note: The projects.agent.knowledgeBases resource is deprecated; only use projects.knowledgeBases.
Instructs the speech synthesizer on how to generate the output audio content. If this audio config is supplied in a request, it overrides all existing text-to-speech settings applied to the agent.
Represents the query input. It can contain either: 1. An audio config which instructs the speech recognizer how to process the speech audio. 2. A conversational query in the form of text. 3. An event that specifies which intent to trigger.
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.
The type of Human Agent Assistant API suggestion to perform, and the maximum number of results to return for that type. Multiple Feature objects can be specified in the features list.
One response of different type of suggestion response which is used in the response of Participants.AnalyzeContent and Participants.AnalyzeContent, as well as HumanAgentAssistantEvent.
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. For more information, see the versions and environments guide.
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.
Deletes entity types in the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates/Creates multiple entity types in the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: BatchUpdateEntityTypesResponse Note: You should always train an agent prior to sending it queries. See the training documentation.
Creates multiple new entities in the specified entity type. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Deletes entities in the specified entity type. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates or creates multiple entities in the specified entity type. This method does not affect entities in the entity type that aren’t explicitly specified in the request. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates the specified agent environment. This method allows you to deploy new agent versions into the environment. When an environment is pointed to a new agent version by setting environment.agent_version, the environment is temporarily set to the LOADING state. During that time, the environment continues serving the previous version of the agent. After the new agent version is done loading, the environment is set back to the RUNNING state. You can use “-” as Environment ID in environment name to update an agent version in the default environment. WARNING: this will negate all recent changes to the draft agent and can’t be undone. You may want to save the draft agent to a version before calling this method.
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. If you might use Agent Assist or other CCAI products now or in the future, consider using AnalyzeContent instead of DetectIntent. AnalyzeContent has additional functionality for Agent Assist and other CCAI products. Note: Always use agent versions for production traffic. See Versions and environments.
Creates a session entity type. If the specified session entity type already exists, overrides the session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Deletes the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Retrieves the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Returns the list of all session entity types in the specified session. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Updates the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Exports the specified agent to a ZIP file. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: ExportAgentResponse
Imports the specified agent from a ZIP file. Uploads new intents and entity types without deleting the existing ones. Intents and entity types with the same name are replaced with the new versions from ImportAgentRequest. After the import, the imported draft agent will be trained automatically (unless disabled in agent settings). However, once the import is done, training may not be completed yet. Please call TrainAgent and wait for the operation it returns in order to train explicitly. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message The operation only tracks when importing is complete, not when it is done training. Note: You should always train an agent prior to sending it queries. See the training documentation.
Deletes intents in the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates/Creates multiple intents in the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: BatchUpdateIntentsResponse Note: You should always train an agent prior to sending it queries. See the training documentation.
Deletes the specified intent and its direct or indirect followup intents. Note: You should always train an agent prior to sending it queries. See the training documentation.
Creates a new document. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document
Deletes the specified document. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: An Empty message
Updates the specified document. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document
Reloads the specified document from its specified source, content_uri or content. The previously loaded content of the document will be deleted. Note: Even when the content of the document has not changed, there still may be side effects because of internal implementation changes. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document Note: The projects.agent.knowledgeBases.documents resource is deprecated; only use projects.knowledgeBases.documents.
Restores the specified agent from a ZIP file. Replaces the current agent version with a new one. All the intents and entity types in the older version are deleted. After the restore, the restored draft agent will be trained automatically (unless disabled in agent settings). However, once the restore is done, training may not be completed yet. Please call TrainAgent and wait for the operation it returns in order to train explicitly. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message The operation only tracks when restoring is complete, not when it is done training. Note: You should always train an agent prior to sending it queries. See the training documentation.
Returns the list of agents. Since there is at most one conversational agent per project, this method is useful primarily for listing all agents across projects the caller has access to. One can achieve that with a wildcard project collection id “-”. Refer to List Sub-Collections.
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. If you might use Agent Assist or other CCAI products now or in the future, consider using AnalyzeContent instead of DetectIntent. AnalyzeContent has additional functionality for Agent Assist and other CCAI products. Note: Always use agent versions for production traffic. See Versions and environments.
Creates a session entity type. If the specified session entity type already exists, overrides the session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Deletes the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Retrieves the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Returns the list of all session entity types in the specified session. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Updates the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Trains the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates the specified agent version. Note that this method does not allow you to update the state of the agent the given version points to. It allows you to update only mutable properties of the version resource.
Creates a new conversation. Conversations are auto-completed after 24 hours. Conversation Lifecycle: There are two stages during a conversation: Automated Agent Stage and Assist Stage. For Automated Agent Stage, there will be a dialogflow agent responding to user queries. For Assist Stage, there’s no dialogflow agent responding to user queries. But we will provide suggestions which are generated from conversation. If Conversation.conversation_profile is configured for a dialogflow agent, conversation will start from Automated Agent Stage, otherwise, it will start from Assist Stage. And during Automated Agent Stage, once an Intent with Intent.live_agent_handoff is triggered, conversation will transfer to Assist Stage.
Import data into the specified conversation dataset. Note that it is not allowed to import data to a conversation dataset that already has data in it. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: ImportConversationDataOperationMetadata - response: ImportConversationDataOperationResponse
Lists messages that belong to a given conversation. messages are ordered by create_time in descending order. To fetch updates without duplication, send request with filter create_time_epoch_microseconds > [first item's create_time of previous request] and empty page_token.
Creates a model. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: CreateConversationModelOperationMetadata - response: ConversationModel
Deletes a model. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: DeleteConversationModelOperationMetadata - response: An Empty message
Deploys a model. If a model is already deployed, deploying it has no effect. A model can only serve prediction requests after it gets deployed. For article suggestion, custom model will not be used unless it is deployed. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: DeployConversationModelOperationMetadata - response: An Empty message
Undeploys a model. If the model is not deployed this method has no effect. If the model is currently being used: - For article suggestion, article suggestion will fallback to the default model if model is undeployed. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: UndeployConversationModelOperationMetadata - response: An Empty message
Adds a text (chat, for example), or audio (phone recording, for example) message from a participant into the conversation. Note: Always use agent versions for production traffic sent to virtual agents. See Versions and environments.
Clears a suggestion feature from a conversation profile for the given participant role. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: ClearSuggestionFeatureConfigOperationMetadata - response: ConversationProfile
Creates a conversation profile in the specified project. ConversationProfile.CreateTime and ConversationProfile.UpdateTime aren’t populated in the response. You can retrieve them via GetConversationProfile API.
Updates the specified conversation profile. ConversationProfile.CreateTime and ConversationProfile.UpdateTime aren’t populated in the response. You can retrieve them via GetConversationProfile API.
Adds or updates a suggestion feature in a conversation profile. If the conversation profile contains the type of suggestion feature for the participant role, it will update it. Otherwise it will insert the suggestion feature. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: SetSuggestionFeatureConfigOperationMetadata - response: ConversationProfile If a long running operation to add or update suggestion feature config for the same conversation profile, participant role and suggestion feature type exists, please cancel the existing long running operation before sending such request, otherwise the request will be rejected.
Suggests summary for a conversation based on specific historical messages. The range of the messages to be used for summary can be specified in the request.
Creates a new document. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document
Deletes the specified document. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: An Empty message
Exports a smart messaging candidate document into the specified destination. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document
Creates documents by importing data from external sources. Dialogflow supports up to 350 documents in each request. If you try to import more, Dialogflow will return an error. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: ImportDocumentsResponse
Updates the specified document. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document
Reloads the specified document from its specified source, content_uri or content. The previously loaded content of the document will be deleted. Note: Even when the content of the document has not changed, there still may be side effects because of internal implementation changes. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document Note: The projects.agent.knowledgeBases.documents resource is deprecated; only use projects.knowledgeBases.documents.
Deletes entity types in the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates/Creates multiple entity types in the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: BatchUpdateEntityTypesResponse Note: You should always train an agent prior to sending it queries. See the training documentation.
Creates multiple new entities in the specified entity type. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Deletes entities in the specified entity type. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates or creates multiple entities in the specified entity type. This method does not affect entities in the entity type that aren’t explicitly specified in the request. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates the specified agent environment. This method allows you to deploy new agent versions into the environment. When an environment is pointed to a new agent version by setting environment.agent_version, the environment is temporarily set to the LOADING state. During that time, the environment continues serving the previous version of the agent. After the new agent version is done loading, the environment is set back to the RUNNING state. You can use “-” as Environment ID in environment name to update an agent version in the default environment. WARNING: this will negate all recent changes to the draft agent and can’t be undone. You may want to save the draft agent to a version before calling this method.
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. If you might use Agent Assist or other CCAI products now or in the future, consider using AnalyzeContent instead of DetectIntent. AnalyzeContent has additional functionality for Agent Assist and other CCAI products. Note: Always use agent versions for production traffic. See Versions and environments.
Creates a session entity type. If the specified session entity type already exists, overrides the session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Deletes the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Retrieves the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Returns the list of all session entity types in the specified session. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Updates the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Exports the specified agent to a ZIP file. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: ExportAgentResponse
Imports the specified agent from a ZIP file. Uploads new intents and entity types without deleting the existing ones. Intents and entity types with the same name are replaced with the new versions from ImportAgentRequest. After the import, the imported draft agent will be trained automatically (unless disabled in agent settings). However, once the import is done, training may not be completed yet. Please call TrainAgent and wait for the operation it returns in order to train explicitly. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message The operation only tracks when importing is complete, not when it is done training. Note: You should always train an agent prior to sending it queries. See the training documentation.
Deletes intents in the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates/Creates multiple intents in the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: BatchUpdateIntentsResponse Note: You should always train an agent prior to sending it queries. See the training documentation.
Deletes the specified intent and its direct or indirect followup intents. Note: You should always train an agent prior to sending it queries. See the training documentation.
Restores the specified agent from a ZIP file. Replaces the current agent version with a new one. All the intents and entity types in the older version are deleted. After the restore, the restored draft agent will be trained automatically (unless disabled in agent settings). However, once the restore is done, training may not be completed yet. Please call TrainAgent and wait for the operation it returns in order to train explicitly. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message The operation only tracks when restoring is complete, not when it is done training. Note: You should always train an agent prior to sending it queries. See the training documentation.
Returns the list of agents. Since there is at most one conversational agent per project, this method is useful primarily for listing all agents across projects the caller has access to. One can achieve that with a wildcard project collection id “-”. Refer to List Sub-Collections.
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. If you might use Agent Assist or other CCAI products now or in the future, consider using AnalyzeContent instead of DetectIntent. AnalyzeContent has additional functionality for Agent Assist and other CCAI products. Note: Always use agent versions for production traffic. See Versions and environments.
Creates a session entity type. If the specified session entity type already exists, overrides the session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Deletes the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Retrieves the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Returns the list of all session entity types in the specified session. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Updates the specified session entity type. This method doesn’t work with Google Assistant integration. Contact Dialogflow support if you need to use session entities with Google Assistant integration.
Trains the specified agent. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: An empty Struct message - response: An Empty message Note: You should always train an agent prior to sending it queries. See the training documentation.
Updates the specified agent version. Note that this method does not allow you to update the state of the agent the given version points to. It allows you to update only mutable properties of the version resource.
Creates a new conversation. Conversations are auto-completed after 24 hours. Conversation Lifecycle: There are two stages during a conversation: Automated Agent Stage and Assist Stage. For Automated Agent Stage, there will be a dialogflow agent responding to user queries. For Assist Stage, there’s no dialogflow agent responding to user queries. But we will provide suggestions which are generated from conversation. If Conversation.conversation_profile is configured for a dialogflow agent, conversation will start from Automated Agent Stage, otherwise, it will start from Assist Stage. And during Automated Agent Stage, once an Intent with Intent.live_agent_handoff is triggered, conversation will transfer to Assist Stage.
Creates a new conversation dataset. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: CreateConversationDatasetOperationMetadata - response: ConversationDataset
Deletes the specified conversation dataset. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: DeleteConversationDatasetOperationMetadata - response: An Empty message
Import data into the specified conversation dataset. Note that it is not allowed to import data to a conversation dataset that already has data in it. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: ImportConversationDataOperationMetadata - response: ImportConversationDataOperationResponse
Lists messages that belong to a given conversation. messages are ordered by create_time in descending order. To fetch updates without duplication, send request with filter create_time_epoch_microseconds > [first item's create_time of previous request] and empty page_token.
Creates a model. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: CreateConversationModelOperationMetadata - response: ConversationModel
Deletes a model. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: DeleteConversationModelOperationMetadata - response: An Empty message
Deploys a model. If a model is already deployed, deploying it has no effect. A model can only serve prediction requests after it gets deployed. For article suggestion, custom model will not be used unless it is deployed. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: DeployConversationModelOperationMetadata - response: An Empty message
Undeploys a model. If the model is not deployed this method has no effect. If the model is currently being used: - For article suggestion, article suggestion will fallback to the default model if model is undeployed. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: UndeployConversationModelOperationMetadata - response: An Empty message
Adds a text (chat, for example), or audio (phone recording, for example) message from a participant into the conversation. Note: Always use agent versions for production traffic sent to virtual agents. See Versions and environments.
Clears a suggestion feature from a conversation profile for the given participant role. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: ClearSuggestionFeatureConfigOperationMetadata - response: ConversationProfile
Creates a conversation profile in the specified project. ConversationProfile.CreateTime and ConversationProfile.UpdateTime aren’t populated in the response. You can retrieve them via GetConversationProfile API.
Updates the specified conversation profile. ConversationProfile.CreateTime and ConversationProfile.UpdateTime aren’t populated in the response. You can retrieve them via GetConversationProfile API.
Adds or updates a suggestion feature in a conversation profile. If the conversation profile contains the type of suggestion feature for the participant role, it will update it. Otherwise it will insert the suggestion feature. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: SetSuggestionFeatureConfigOperationMetadata - response: ConversationProfile If a long running operation to add or update suggestion feature config for the same conversation profile, participant role and suggestion feature type exists, please cancel the existing long running operation before sending such request, otherwise the request will be rejected.
Suggests summary for a conversation based on specific historical messages. The range of the messages to be used for summary can be specified in the request.
Creates a new document. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document
Deletes the specified document. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: An Empty message
Exports a smart messaging candidate document into the specified destination. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document
Creates documents by importing data from external sources. Dialogflow supports up to 350 documents in each request. If you try to import more, Dialogflow will return an error. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: ImportDocumentsResponse
Updates the specified document. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document
Reloads the specified document from its specified source, content_uri or content. The previously loaded content of the document will be deleted. Note: Even when the content of the document has not changed, there still may be side effects because of internal implementation changes. This method is a long-running operation. The returned Operation type has the following method-specific fields: - metadata: KnowledgeOperationMetadata - response: Document Note: The projects.agent.knowledgeBases.documents resource is deprecated; only use projects.knowledgeBases.documents.
Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn’t support this method, it returns google.rpc.Code.UNIMPLEMENTED. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to Code.CANCELLED.
Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.
Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn’t support this method, it returns google.rpc.Code.UNIMPLEMENTED. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to Code.CANCELLED.
Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.