// Copyright 2024 Google LLC // // Licensed under the Apache License, Version 2.0 (the "License"); // you may not use this file except in compliance with the License. // You may obtain a copy of the License at // // http://www.apache.org/licenses/LICENSE-2.0 // // Unless required by applicable law or agreed to in writing, software // distributed under the License is distributed on an "AS IS" BASIS, // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. // See the License for the specific language governing permissions and // limitations under the License. syntax = "proto3"; package google.cloud.dialogflow.cx.v3beta1; import "google/api/annotations.proto"; import "google/api/client.proto"; import "google/api/field_behavior.proto"; import "google/api/resource.proto"; import "google/cloud/dialogflow/cx/v3beta1/advanced_settings.proto"; import "google/cloud/dialogflow/cx/v3beta1/audio_config.proto"; import "google/cloud/dialogflow/cx/v3beta1/data_store_connection.proto"; import "google/cloud/dialogflow/cx/v3beta1/example.proto"; import "google/cloud/dialogflow/cx/v3beta1/flow.proto"; import "google/cloud/dialogflow/cx/v3beta1/generative_settings.proto"; import "google/cloud/dialogflow/cx/v3beta1/intent.proto"; import "google/cloud/dialogflow/cx/v3beta1/page.proto"; import "google/cloud/dialogflow/cx/v3beta1/response_message.proto"; import "google/cloud/dialogflow/cx/v3beta1/session_entity_type.proto"; import "google/cloud/dialogflow/cx/v3beta1/tool_call.proto"; import "google/protobuf/duration.proto"; import "google/protobuf/field_mask.proto"; import "google/protobuf/struct.proto"; import "google/rpc/status.proto"; import "google/type/latlng.proto"; option cc_enable_arenas = true; option csharp_namespace = "Google.Cloud.Dialogflow.Cx.V3Beta1"; option go_package = "cloud.google.com/go/dialogflow/cx/apiv3beta1/cxpb;cxpb"; option java_multiple_files = true; option java_outer_classname = "SessionProto"; option java_package = "com.google.cloud.dialogflow.cx.v3beta1"; option objc_class_prefix = "DF"; option ruby_package = "Google::Cloud::Dialogflow::CX::V3beta1"; option (google.api.resource_definition) = { type: "dialogflow.googleapis.com/Session" pattern: "projects/{project}/locations/{location}/agents/{agent}/sessions/{session}" pattern: "projects/{project}/locations/{location}/agents/{agent}/environments/{environment}/sessions/{session}" }; option (google.api.resource_definition) = { type: "discoveryengine.googleapis.com/DataStore" pattern: "projects/{project}/locations/{location}/dataStores/{data_store}" pattern: "projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}" }; // A session represents an interaction with a user. You retrieve user input // and pass it to the // [DetectIntent][google.cloud.dialogflow.cx.v3beta1.Sessions.DetectIntent] // method to determine user intent and respond. service Sessions { option (google.api.default_host) = "dialogflow.googleapis.com"; option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform," "https://www.googleapis.com/auth/dialogflow"; // Processes a natural language query and returns structured, actionable data // as a result. This method is not idempotent, because it may cause session // entity types to be updated, which in turn might affect results of future // queries. // // Note: Always use agent versions for production traffic. // See [Versions and // environments](https://cloud.google.com/dialogflow/cx/docs/concept/version). rpc DetectIntent(DetectIntentRequest) returns (DetectIntentResponse) { option (google.api.http) = { post: "/v3beta1/{session=projects/*/locations/*/agents/*/sessions/*}:detectIntent" body: "*" additional_bindings { post: "/v3beta1/{session=projects/*/locations/*/agents/*/environments/*/sessions/*}:detectIntent" body: "*" } }; } // Processes a natural language query and returns structured, actionable data // as a result through server-side streaming. Server-side streaming allows // Dialogflow to send [partial // responses](https://cloud.google.com/dialogflow/cx/docs/concept/fulfillment#partial-response) // earlier in a single request. rpc ServerStreamingDetectIntent(DetectIntentRequest) returns (stream DetectIntentResponse) { option (google.api.http) = { post: "/v3beta1/{session=projects/*/locations/*/agents/*/sessions/*}:serverStreamingDetectIntent" body: "*" additional_bindings { post: "/v3beta1/{session=projects/*/locations/*/agents/*/environments/*/sessions/*}:serverStreamingDetectIntent" body: "*" } }; } // Processes a natural language query in audio format in a streaming fashion // and returns structured, actionable data as a result. This method is only // available via the gRPC API (not REST). // // Note: Always use agent versions for production traffic. // See [Versions and // environments](https://cloud.google.com/dialogflow/cx/docs/concept/version). rpc StreamingDetectIntent(stream StreamingDetectIntentRequest) returns (stream StreamingDetectIntentResponse) {} // Returns preliminary intent match results, doesn't change the session // status. rpc MatchIntent(MatchIntentRequest) returns (MatchIntentResponse) { option (google.api.http) = { post: "/v3beta1/{session=projects/*/locations/*/agents/*/sessions/*}:matchIntent" body: "*" additional_bindings { post: "/v3beta1/{session=projects/*/locations/*/agents/*/environments/*/sessions/*}:matchIntent" body: "*" } }; } // Fulfills a matched intent returned by // [MatchIntent][google.cloud.dialogflow.cx.v3beta1.Sessions.MatchIntent]. // Must be called after // [MatchIntent][google.cloud.dialogflow.cx.v3beta1.Sessions.MatchIntent], // with input from // [MatchIntentResponse][google.cloud.dialogflow.cx.v3beta1.MatchIntentResponse]. // Otherwise, the behavior is undefined. rpc FulfillIntent(FulfillIntentRequest) returns (FulfillIntentResponse) { option (google.api.http) = { post: "/v3beta1/{match_intent_request.session=projects/*/locations/*/agents/*/sessions/*}:fulfillIntent" body: "*" additional_bindings { post: "/v3beta1/{match_intent_request.session=projects/*/locations/*/agents/*/environments/*/sessions/*}:fulfillIntent" body: "*" } }; } // Updates the feedback received from the user for a single turn of the bot // response. rpc SubmitAnswerFeedback(SubmitAnswerFeedbackRequest) returns (AnswerFeedback) { option (google.api.http) = { post: "/v3beta1/{session=projects/*/locations/*/agents/*/sessions/*}:submitAnswerFeedback" body: "*" }; } } // Stores information about feedback provided by users about a response. message AnswerFeedback { // Represents thumbs up/down rating provided by user about a response. enum Rating { // Rating not specified. RATING_UNSPECIFIED = 0; // Thumbs up feedback from user. THUMBS_UP = 1; // Thumbs down feedback from user. THUMBS_DOWN = 2; } // Stores extra information about why users provided thumbs down rating. message RatingReason { // Optional. Custom reason labels for thumbs down rating provided by the // user. The maximum number of labels allowed is 10 and the maximum length // of a single label is 128 characters. repeated string reason_labels = 3 [(google.api.field_behavior) = OPTIONAL]; // Optional. Additional feedback about the rating. // This field can be populated without choosing a predefined `reason`. string feedback = 2 [(google.api.field_behavior) = OPTIONAL]; } // Optional. Rating from user for the specific Dialogflow response. Rating rating = 1 [(google.api.field_behavior) = OPTIONAL]; // Optional. In case of thumbs down rating provided, users can optionally // provide context about the rating. RatingReason rating_reason = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. Custom rating from the user about the provided answer, with // maximum length of 1024 characters. For example, client could use a // customized JSON object to indicate the rating. string custom_rating = 3 [(google.api.field_behavior) = OPTIONAL]; } // The request to set the feedback for a bot answer. message SubmitAnswerFeedbackRequest { // Required. The name of the session the feedback was sent to. string session = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "dialogflow.googleapis.com/Session" } ]; // Required. ID of the response to update its feedback. This is the same as // DetectIntentResponse.response_id. string response_id = 2 [(google.api.field_behavior) = REQUIRED]; // Required. Feedback provided for a bot answer. AnswerFeedback answer_feedback = 3 [(google.api.field_behavior) = REQUIRED]; // Optional. The mask to control which fields to update. If the mask is not // present, all fields will be updated. google.protobuf.FieldMask update_mask = 4 [(google.api.field_behavior) = OPTIONAL]; } // The request to detect user's intent. message DetectIntentRequest { // Required. The name of the session this query is sent to. // Format: `projects//locations//agents//sessions/` or `projects//locations//agents//environments//sessions/`. // If `Environment ID` is not specified, we assume default 'draft' // environment. // It's up to the API caller to choose an appropriate `Session ID`. It can be // a random number or some type of session identifiers (preferably hashed). // The length of the `Session ID` must not exceed 36 characters. // // For more information, see the [sessions // guide](https://cloud.google.com/dialogflow/cx/docs/concept/session). // // Note: Always use agent versions for production traffic. // See [Versions and // environments](https://cloud.google.com/dialogflow/cx/docs/concept/version). string session = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "dialogflow.googleapis.com/Session" } ]; // The parameters of this query. QueryParameters query_params = 2; // Required. The input specification. QueryInput query_input = 3 [(google.api.field_behavior) = REQUIRED]; // Instructs the speech synthesizer how to generate the output audio. OutputAudioConfig output_audio_config = 4; } // The message returned from the DetectIntent method. message DetectIntentResponse { // Represents different DetectIntentResponse types. enum ResponseType { // Not specified. This should never happen. RESPONSE_TYPE_UNSPECIFIED = 0; // Partial response. e.g. Aggregated responses in a Fulfillment that enables // `return_partial_response` can be returned as partial response. // WARNING: partial response is not eligible for barge-in. PARTIAL = 1; // Final response. FINAL = 2; } // Output only. The unique identifier of the response. It can be used to // locate a response in the training example set or for reporting issues. string response_id = 1; // The result of the conversational query. QueryResult query_result = 2; // The audio data bytes encoded as specified in the request. // Note: The output audio is generated based on the values of default platform // text responses found in the // [`query_result.response_messages`][google.cloud.dialogflow.cx.v3beta1.QueryResult.response_messages] // field. If multiple default text responses exist, they will be concatenated // when generating audio. If no default platform text responses exist, the // generated audio content will be empty. // // In some scenarios, multiple output audio fields may be present in the // response structure. In these cases, only the top-most-level audio output // has content. bytes output_audio = 4; // The config used by the speech synthesizer to generate the output audio. OutputAudioConfig output_audio_config = 5; // Response type. ResponseType response_type = 6; // Indicates whether the partial response can be cancelled when a later // response arrives. e.g. if the agent specified some music as partial // response, it can be cancelled. bool allow_cancellation = 7; } // The top-level message sent by the client to the // [Sessions.StreamingDetectIntent][google.cloud.dialogflow.cx.v3beta1.Sessions.StreamingDetectIntent] // method. // // Multiple request messages should be sent in order: // // 1. The first message must contain // [session][google.cloud.dialogflow.cx.v3beta1.StreamingDetectIntentRequest.session], // [query_input][google.cloud.dialogflow.cx.v3beta1.StreamingDetectIntentRequest.query_input] // plus optionally // [query_params][google.cloud.dialogflow.cx.v3beta1.StreamingDetectIntentRequest.query_params]. // If the client wants to receive an audio response, it should also contain // [output_audio_config][google.cloud.dialogflow.cx.v3beta1.StreamingDetectIntentRequest.output_audio_config]. // // 2. If // [query_input][google.cloud.dialogflow.cx.v3beta1.StreamingDetectIntentRequest.query_input] // was set to // [query_input.audio.config][google.cloud.dialogflow.cx.v3beta1.AudioInput.config], // all subsequent messages must contain // [query_input.audio.audio][google.cloud.dialogflow.cx.v3beta1.AudioInput.audio] // to continue with Speech recognition. If you decide to rather detect an // intent from text input after you already started Speech recognition, // please send a message with // [query_input.text][google.cloud.dialogflow.cx.v3beta1.QueryInput.text]. // // However, note that: // // * Dialogflow will bill you for the audio duration so far. // * Dialogflow discards all Speech recognition results in favor of the // input text. // * Dialogflow will use the language code from the first message. // // After you sent all input, you must half-close or abort the request stream. message StreamingDetectIntentRequest { // The name of the session this query is sent to. // Format: `projects//locations//agents//sessions/` or `projects//locations//agents//environments//sessions/`. // If `Environment ID` is not specified, we assume default 'draft' // environment. // It's up to the API caller to choose an appropriate `Session ID`. It can be // a random number or some type of session identifiers (preferably hashed). // The length of the `Session ID` must not exceed 36 characters. // Note: session must be set in the first request. // // For more information, see the [sessions // guide](https://cloud.google.com/dialogflow/cx/docs/concept/session). // // Note: Always use agent versions for production traffic. // See [Versions and // environments](https://cloud.google.com/dialogflow/cx/docs/concept/version). string session = 1 [(google.api.resource_reference) = { type: "dialogflow.googleapis.com/Session" }]; // The parameters of this query. QueryParameters query_params = 2; // Required. The input specification. QueryInput query_input = 3 [(google.api.field_behavior) = REQUIRED]; // Instructs the speech synthesizer how to generate the output audio. OutputAudioConfig output_audio_config = 4; // Enable partial detect intent response. If this flag is not enabled, // response stream still contains only one final `DetectIntentResponse` even // if some `Fulfillment`s in the agent have been configured to return partial // responses. bool enable_partial_response = 5; // If true, `StreamingDetectIntentResponse.debugging_info` will get populated. bool enable_debugging_info = 8; } // Cloud conversation info for easier debugging. // It will get populated in `StreamingDetectIntentResponse` or // `StreamingAnalyzeContentResponse` when the flag `enable_debugging_info` is // set to true in corresponding requests. message CloudConversationDebuggingInfo { // Number of input audio data chunks in streaming requests. int32 audio_data_chunks = 1; // Time offset of the end of speech utterance relative to the // beginning of the first audio chunk. google.protobuf.Duration result_end_time_offset = 2; // Duration of first audio chunk. google.protobuf.Duration first_audio_duration = 3; // Whether client used single utterance mode. bool single_utterance = 5; // Time offsets of the speech partial results relative to the beginning of // the stream. repeated google.protobuf.Duration speech_partial_results_end_times = 6; // Time offsets of the speech final results (is_final=true) relative to the // beginning of the stream. repeated google.protobuf.Duration speech_final_results_end_times = 7; // Total number of partial responses. int32 partial_responses = 8; // Time offset of Speaker ID stream close time relative to the Speech stream // close time in milliseconds. Only meaningful for conversations involving // passive verification. int32 speaker_id_passive_latency_ms_offset = 9; // Whether a barge-in event is triggered in this request. bool bargein_event_triggered = 10; // Whether speech uses single utterance mode. bool speech_single_utterance = 11; // Time offsets of the DTMF partial results relative to the beginning of // the stream. repeated google.protobuf.Duration dtmf_partial_results_times = 12; // Time offsets of the DTMF final results relative to the beginning of // the stream. repeated google.protobuf.Duration dtmf_final_results_times = 13; // Time offset of the end-of-single-utterance signal relative to the // beginning of the stream. google.protobuf.Duration single_utterance_end_time_offset = 14; // No speech timeout settings for the stream. google.protobuf.Duration no_speech_timeout = 15; // Speech endpointing timeout settings for the stream. google.protobuf.Duration endpointing_timeout = 19; // Whether the streaming terminates with an injected text query. bool is_input_text = 16; // Client half close time in terms of input audio duration. google.protobuf.Duration client_half_close_time_offset = 17; // Client half close time in terms of API streaming duration. google.protobuf.Duration client_half_close_streaming_time_offset = 18; } // The top-level message returned from the // [StreamingDetectIntent][google.cloud.dialogflow.cx.v3beta1.Sessions.StreamingDetectIntent] // method. // // Multiple response messages (N) can be returned in order. // // The first (N-1) responses set either the `recognition_result` or // `detect_intent_response` field, depending on the request: // // * If the `StreamingDetectIntentRequest.query_input.audio` field was // set, and the `StreamingDetectIntentRequest.enable_partial_response` // field was false, the `recognition_result` field is populated for each // of the (N-1) responses. // See the // [StreamingRecognitionResult][google.cloud.dialogflow.cx.v3beta1.StreamingRecognitionResult] // message for details about the result message sequence. // // * If the `StreamingDetectIntentRequest.enable_partial_response` field was // true, the `detect_intent_response` field is populated for each // of the (N-1) responses, where 1 <= N <= 4. // These responses set the // [DetectIntentResponse.response_type][google.cloud.dialogflow.cx.v3beta1.DetectIntentResponse.response_type] // field to `PARTIAL`. // // For the final Nth response message, the `detect_intent_response` is fully // populated, and // [DetectIntentResponse.response_type][google.cloud.dialogflow.cx.v3beta1.DetectIntentResponse.response_type] // is set to `FINAL`. message StreamingDetectIntentResponse { // The output response. oneof response { // The result of speech recognition. StreamingRecognitionResult recognition_result = 1; // The response from detect intent. DetectIntentResponse detect_intent_response = 2; } // Debugging info that would get populated when // `StreamingDetectIntentRequest.enable_debugging_info` is set to true. CloudConversationDebuggingInfo debugging_info = 4; } // Contains a speech recognition result corresponding to a portion of the audio // that is currently being processed or an indication that this is the end // of the single requested utterance. // // While end-user audio is being processed, Dialogflow sends a series of // results. Each result may contain a `transcript` value. A transcript // represents a portion of the utterance. While the recognizer is processing // audio, transcript values may be interim values or finalized values. // Once a transcript is finalized, the `is_final` value is set to true and // processing continues for the next transcript. // // If `StreamingDetectIntentRequest.query_input.audio.config.single_utterance` // was true, and the recognizer has completed processing audio, // the `message_type` value is set to `END_OF_SINGLE_UTTERANCE and the // following (last) result contains the last finalized transcript. // // The complete end-user utterance is determined by concatenating the // finalized transcript values received for the series of results. // // In the following example, single utterance is enabled. In the case where // single utterance is not enabled, result 7 would not occur. // // ``` // Num | transcript | message_type | is_final // --- | ----------------------- | ----------------------- | -------- // 1 | "tube" | TRANSCRIPT | false // 2 | "to be a" | TRANSCRIPT | false // 3 | "to be" | TRANSCRIPT | false // 4 | "to be or not to be" | TRANSCRIPT | true // 5 | "that's" | TRANSCRIPT | false // 6 | "that is | TRANSCRIPT | false // 7 | unset | END_OF_SINGLE_UTTERANCE | unset // 8 | " that is the question" | TRANSCRIPT | true // ``` // // Concatenating the finalized transcripts with `is_final` set to true, // the complete utterance becomes "to be or not to be that is the question". message StreamingRecognitionResult { // Type of the response message. enum MessageType { // Not specified. Should never be used. MESSAGE_TYPE_UNSPECIFIED = 0; // Message contains a (possibly partial) transcript. TRANSCRIPT = 1; // This event indicates that the server has detected the end of the user's // speech utterance and expects no additional speech. Therefore, the server // will not process additional audio (although it may subsequently return // additional results). The client should stop sending additional audio // data, half-close the gRPC connection, and wait for any additional results // until the server closes the gRPC connection. This message is only sent if // [`single_utterance`][google.cloud.dialogflow.cx.v3beta1.InputAudioConfig.single_utterance] // was set to `true`, and is not used otherwise. END_OF_SINGLE_UTTERANCE = 2; } // Type of the result message. MessageType message_type = 1; // Transcript text representing the words that the user spoke. // Populated if and only if `message_type` = `TRANSCRIPT`. string transcript = 2; // If `false`, the `StreamingRecognitionResult` represents an // interim result that may change. If `true`, the recognizer will not return // any further hypotheses about this piece of the audio. May only be populated // for `message_type` = `TRANSCRIPT`. bool is_final = 3; // The Speech confidence between 0.0 and 1.0 for the current portion of audio. // A higher number indicates an estimated greater likelihood that the // recognized words are correct. The default of 0.0 is a sentinel value // indicating that confidence was not set. // // This field is typically only provided if `is_final` is true and you should // not rely on it being accurate or even set. float confidence = 4; // An estimate of the likelihood that the speech recognizer will // not change its guess about this interim recognition result: // * If the value is unspecified or 0.0, Dialogflow didn't compute the // stability. In particular, Dialogflow will only provide stability for // `TRANSCRIPT` results with `is_final = false`. // * Otherwise, the value is in (0.0, 1.0] where 0.0 means completely // unstable and 1.0 means completely stable. float stability = 6; // Word-specific information for the words recognized by Speech in // [transcript][google.cloud.dialogflow.cx.v3beta1.StreamingRecognitionResult.transcript]. // Populated if and only if `message_type` = `TRANSCRIPT` and // [InputAudioConfig.enable_word_info] is set. repeated SpeechWordInfo speech_word_info = 7; // Time offset of the end of this Speech recognition result relative to the // beginning of the audio. Only populated for `message_type` = // `TRANSCRIPT`. google.protobuf.Duration speech_end_offset = 8; // Detected language code for the transcript. string language_code = 10; } // Represents the parameters of a conversational query. message QueryParameters { // The time zone of this conversational query from the [time zone // database](https://www.iana.org/time-zones), e.g., America/New_York, // Europe/Paris. If not provided, the time zone specified in the agent is // used. string time_zone = 1; // The geo location of this conversational query. google.type.LatLng geo_location = 2; // Additional session entity types to replace or extend developer entity types // with. The entity synonyms apply to all languages and persist for the // session of this query. repeated SessionEntityType session_entity_types = 3; // This field can be used to pass custom data into the webhook associated with // the agent. Arbitrary JSON objects are supported. // Some integrations that query a Dialogflow agent may provide additional // information in the payload. // In particular, for the Dialogflow Phone Gateway integration, this field has // the form: // ``` // { // "telephony": { // "caller_id": "+18558363987" // } // } // ``` google.protobuf.Struct payload = 4; // Additional parameters to be put into [session // parameters][SessionInfo.parameters]. To remove a // parameter from the session, clients should explicitly set the parameter // value to null. // // You can reference the session parameters in the agent with the following // format: $session.params.parameter-id. // // Depending on your protocol or client library language, this is a // map, associative array, symbol table, dictionary, or JSON object // composed of a collection of (MapKey, MapValue) pairs: // // * MapKey type: string // * MapKey value: parameter name // * MapValue type: If parameter's entity type is a composite entity then use // map, otherwise, depending on the parameter value type, it could be one of // string, number, boolean, null, list or map. // * MapValue value: If parameter's entity type is a composite entity then use // map from composite entity property names to property values, otherwise, // use parameter value. google.protobuf.Struct parameters = 5; // The unique identifier of the // [page][google.cloud.dialogflow.cx.v3beta1.Page] to override the [current // page][QueryResult.current_page] in the session. // Format: `projects//locations//agents//flows//pages/`. // // If `current_page` is specified, the previous state of the session will be // ignored by Dialogflow, including the [previous // page][QueryResult.current_page] and the [previous session // parameters][QueryResult.parameters]. // In most cases, // [current_page][google.cloud.dialogflow.cx.v3beta1.QueryParameters.current_page] // and // [parameters][google.cloud.dialogflow.cx.v3beta1.QueryParameters.parameters] // should be configured together to direct a session to a specific state. string current_page = 6 [ (google.api.resource_reference) = { type: "dialogflow.googleapis.com/Page" } ]; // Whether to disable webhook calls for this request. bool disable_webhook = 7; // Configures whether sentiment analysis should be performed. If not // provided, sentiment analysis is not performed. bool analyze_query_text_sentiment = 8; // This field can be used to pass HTTP headers for a webhook // call. These headers will be sent to webhook along with the headers that // have been configured through Dialogflow web console. The headers defined // within this field will overwrite the headers configured through Dialogflow // console if there is a conflict. Header names are case-insensitive. // Google's specified headers are not allowed. Including: "Host", // "Content-Length", "Connection", "From", "User-Agent", "Accept-Encoding", // "If-Modified-Since", "If-None-Match", "X-Forwarded-For", etc. map webhook_headers = 10; // A list of flow versions to override for the request. // Format: `projects//locations//agents//flows//versions/`. // // If version 1 of flow X is included in this list, the traffic of // flow X will go through version 1 regardless of the version configuration in // the environment. Each flow can have at most one version specified in this // list. repeated string flow_versions = 14 [(google.api.resource_reference) = { type: "dialogflow.googleapis.com/Version" }]; // Optional. Start the session with the specified // [playbook][google.cloud.dialogflow.cx.v3beta1.Playbook]. You can only // specify the playbook at the beginning of the session. Otherwise, an error // will be thrown. // // Format: `projects//locations//agents//playbooks/`. string current_playbook = 19 [ (google.api.field_behavior) = OPTIONAL, (google.api.resource_reference) = { type: "dialogflow.googleapis.com/Playbook" } ]; // Optional. Use the specified LLM model settings for processing the request. LlmModelSettings llm_model_settings = 21 [(google.api.field_behavior) = OPTIONAL]; // The channel which this query is for. // // If specified, only the // [ResponseMessage][google.cloud.dialogflow.cx.v3beta1.ResponseMessage] // associated with the channel will be returned. If no // [ResponseMessage][google.cloud.dialogflow.cx.v3beta1.ResponseMessage] is // associated with the channel, it falls back to the // [ResponseMessage][google.cloud.dialogflow.cx.v3beta1.ResponseMessage] with // unspecified channel. // // If unspecified, the // [ResponseMessage][google.cloud.dialogflow.cx.v3beta1.ResponseMessage] with // unspecified channel will be returned. string channel = 15; // Optional. Configure lifetime of the Dialogflow session. // By default, a Dialogflow session remains active and its data is stored for // 30 minutes after the last request is sent for the session. // This value should be no longer than 1 day. google.protobuf.Duration session_ttl = 16 [(google.api.field_behavior) = OPTIONAL]; // Optional. Information about the end-user to improve the relevance and // accuracy of generative answers. // // This will be interpreted and used by a language model, so, for good // results, the data should be self-descriptive, and in a simple structure. // // Example: // // ```json // { // "subscription plan": "Business Premium Plus", // "devices owned": [ // {"model": "Google Pixel 7"}, // {"model": "Google Pixel Tablet"} // ] // } // ``` google.protobuf.Struct end_user_metadata = 18 [(google.api.field_behavior) = OPTIONAL]; // Optional. Search configuration for UCS search queries. SearchConfig search_config = 20 [(google.api.field_behavior) = OPTIONAL]; // Optional. If set to true and data stores are involved in serving the // request then // DetectIntentResponse.query_result.data_store_connection_signals // will be filled with data that can help evaluations. bool populate_data_store_connection_signals = 25 [(google.api.field_behavior) = OPTIONAL]; } // Search configuration for UCS search queries. message SearchConfig { // Optional. Boosting configuration for the datastores. repeated BoostSpecs boost_specs = 1 [(google.api.field_behavior) = OPTIONAL]; // Optional. Filter configuration for the datastores. repeated FilterSpecs filter_specs = 2 [(google.api.field_behavior) = OPTIONAL]; } // 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 message BoostSpec { // Boost applies to documents which match a condition. message ConditionBoostSpec { // Optional. An expression which specifies a boost condition. The syntax and // supported fields are the same as a filter expression. // Examples: // // * To boost documents with document ID "doc_1" or "doc_2", and // color // "Red" or "Blue": // * (id: ANY("doc_1", "doc_2")) AND (color: ANY("Red","Blue")) string condition = 1 [(google.api.field_behavior) = OPTIONAL]; // Optional. Strength of the condition boost, which should be in [-1, 1]. // Negative boost means demotion. Default is 0.0. // // Setting to 1.0 gives the document a big promotion. However, it does not // necessarily mean that the boosted document will be the top result at // all times, nor that other documents will be excluded. Results could // still be shown even when none of them matches the condition. And // results that are significantly more relevant to the search query can // still trump your heavily favored but irrelevant documents. // // Setting to -1.0 gives the document a big demotion. However, results // that are deeply relevant might still be shown. The document will have // an upstream battle to get a fairly high ranking, but it is not blocked // out completely. // // Setting to 0.0 means no boost applied. The boosting condition is // ignored. float boost = 2 [(google.api.field_behavior) = OPTIONAL]; } // Optional. Condition boost specifications. If a document matches multiple // conditions in the specifictions, boost scores from these specifications are // all applied and combined in a non-linear way. Maximum number of // specifications is 20. repeated ConditionBoostSpec condition_boost_specs = 1 [(google.api.field_behavior) = OPTIONAL]; } // Boost specifications for data stores. message BoostSpecs { // Optional. Data Stores where the boosting configuration is applied. The full // names of the referenced data stores. Formats: // `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}` // `projects/{project}/locations/{location}/dataStores/{data_store} repeated string data_stores = 1 [ (google.api.field_behavior) = OPTIONAL, (google.api.resource_reference) = { type: "discoveryengine.googleapis.com/DataStore" } ]; // Optional. A list of boosting specifications. repeated BoostSpec spec = 2 [(google.api.field_behavior) = OPTIONAL]; } // Filter specifications for data stores. message FilterSpecs { // Optional. Data Stores where the boosting configuration is applied. The full // names of the referenced data stores. Formats: // `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}` // `projects/{project}/locations/{location}/dataStores/{data_store} repeated string data_stores = 1 [ (google.api.field_behavior) = OPTIONAL, (google.api.resource_reference) = { type: "discoveryengine.googleapis.com/DataStore" } ]; // Optional. The filter expression to be applied. // Expression syntax is documented at // https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata#filter-expression-syntax string filter = 2 [(google.api.field_behavior) = OPTIONAL]; } // 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. message QueryInput { // Required. The input specification. oneof input { // The natural language text to be processed. TextInput text = 2; // The intent to be triggered. IntentInput intent = 3; // The natural language speech audio to be processed. AudioInput audio = 5; // The event to be triggered. EventInput event = 6; // The DTMF event to be handled. DtmfInput dtmf = 7; // The results of a tool executed by the client. google.cloud.dialogflow.cx.v3beta1.ToolCallResult tool_call_result = 11; } // Required. The language of the input. See [Language // Support](https://cloud.google.com/dialogflow/cx/docs/reference/language) // for a list of the currently supported language codes. Note that queries in // the same session do not necessarily need to specify the same language. string language_code = 4 [(google.api.field_behavior) = REQUIRED]; } // Represents the information of a query if handled by generative agent // resources. message GenerativeInfo { // The stack of [playbooks][google.cloud.dialogflow.cx.v3beta1.Playbook] that // the conversation has currently entered, with the most recent one on the // top. repeated string current_playbooks = 1; // The actions performed by the generative playbook for the current agent // response. Example action_tracing_info = 2; } // Represents the result of a conversational query. message QueryResult { // The original conversational query. oneof query { // If [natural language text][google.cloud.dialogflow.cx.v3beta1.TextInput] // was provided as input, this field will contain a copy of the text. string text = 1; // If an [intent][google.cloud.dialogflow.cx.v3beta1.IntentInput] was // provided as input, this field will contain a copy of the intent // identifier. Format: `projects//locations//agents//intents/`. string trigger_intent = 11 [(google.api.resource_reference) = { type: "dialogflow.googleapis.com/Intent" }]; // If [natural language speech // audio][google.cloud.dialogflow.cx.v3beta1.AudioInput] was provided as // input, this field will contain the transcript for the audio. string transcript = 12; // If an [event][google.cloud.dialogflow.cx.v3beta1.EventInput] was provided // as input, this field will contain the name of the event. string trigger_event = 14; // If a [DTMF][google.cloud.dialogflow.cx.v3beta1.DtmfInput] was provided as // input, this field will contain a copy of the // [DtmfInput][google.cloud.dialogflow.cx.v3beta1.DtmfInput]. DtmfInput dtmf = 23; } // The language that was triggered during intent detection. // See [Language // Support](https://cloud.google.com/dialogflow/cx/docs/reference/language) // for a list of the currently supported language codes. string language_code = 2; // The collected [session // parameters][google.cloud.dialogflow.cx.v3beta1.SessionInfo.parameters]. // // Depending on your protocol or client library language, this is a // map, associative array, symbol table, dictionary, or JSON object // composed of a collection of (MapKey, MapValue) pairs: // // * MapKey type: string // * MapKey value: parameter name // * MapValue type: If parameter's entity type is a composite entity then use // map, otherwise, depending on the parameter value type, it could be one of // string, number, boolean, null, list or map. // * MapValue value: If parameter's entity type is a composite entity then use // map from composite entity property names to property values, otherwise, // use parameter value. google.protobuf.Struct parameters = 3; // The list of rich messages returned to the client. Responses vary from // simple text messages to more sophisticated, structured payloads used // to drive complex logic. repeated ResponseMessage response_messages = 4; // The list of webhook ids in the order of call sequence. repeated string webhook_ids = 25; // The list of webhook display names in the order of call sequence. repeated string webhook_display_names = 26; // The list of webhook latencies in the order of call sequence. repeated google.protobuf.Duration webhook_latencies = 27; // The list of webhook tags in the order of call sequence. repeated string webhook_tags = 29; // The list of webhook call status in the order of call sequence. repeated google.rpc.Status webhook_statuses = 13; // The list of webhook payload in // [WebhookResponse.payload][google.cloud.dialogflow.cx.v3beta1.WebhookResponse.payload], // in the order of call sequence. If some webhook call fails or doesn't return // any payload, an empty `Struct` would be used instead. repeated google.protobuf.Struct webhook_payloads = 6; // The current [Page][google.cloud.dialogflow.cx.v3beta1.Page]. Some, not all // fields are filled in this message, including but not limited to `name` and // `display_name`. Page current_page = 7; // The current [Flow][google.cloud.dialogflow.cx.v3beta1.Flow]. Some, not all // fields are filled in this message, including but not limited to `name` and // `display_name`. Flow current_flow = 31; // The [Intent][google.cloud.dialogflow.cx.v3beta1.Intent] that matched the // conversational query. Some, not all fields are filled in this message, // including but not limited to: `name` and `display_name`. This field is // deprecated, please use // [QueryResult.match][google.cloud.dialogflow.cx.v3beta1.QueryResult.match] // instead. Intent intent = 8 [deprecated = true]; // The intent detection confidence. Values range from 0.0 (completely // uncertain) to 1.0 (completely certain). // This value is for informational purpose only and is only used to // help match the best intent within the classification threshold. // This value may change for the same end-user expression at any time due to a // model retraining or change in implementation. // This field is deprecated, please use // [QueryResult.match][google.cloud.dialogflow.cx.v3beta1.QueryResult.match] // instead. float intent_detection_confidence = 9 [deprecated = true]; // Intent match result, could be an intent or an event. Match match = 15; // The free-form diagnostic info. For example, this field could contain // webhook call latency. The fields of this data can change without notice, // so you should not write code that depends on its structure. // // One of the fields is called "Alternative Matched Intents", which may // aid with debugging. The following describes these intent results: // // - The list is empty if no intent was matched to end-user input. // - Only intents that are referenced in the currently active flow are // included. // - The matched intent is included. // - Other intents that could have matched end-user input, but did not match // because they are referenced by intent routes that are out of // [scope](https://cloud.google.com/dialogflow/cx/docs/concept/handler#scope), // are included. // - Other intents referenced by intent routes in scope that matched end-user // input, but had a lower confidence score. google.protobuf.Struct diagnostic_info = 10; // The information of a query if handled by generative agent resources. GenerativeInfo generative_info = 33; // The sentiment analyss result, which depends on // [`analyze_query_text_sentiment`] // [google.cloud.dialogflow.cx.v3beta1.QueryParameters.analyze_query_text_sentiment], // specified in the request. SentimentAnalysisResult sentiment_analysis_result = 17; // Returns the current advanced settings including IVR settings. Even though // the operations configured by these settings are performed by Dialogflow, // the client may need to perform special logic at the moment. For example, if // Dialogflow exports audio to Google Cloud Storage, then the client may need // to wait for the resulting object to appear in the bucket before proceeding. AdvancedSettings advanced_settings = 21; // Indicates whether the Thumbs up/Thumbs down rating controls are need to be // shown for the response in the Dialogflow Messenger widget. bool allow_answer_feedback = 32; // Optional. Data store connection feature output signals. // Filled only when data stores are involved in serving the query and // DetectIntentRequest.populate data_store_connection_quality_signals is set // to true in the request. DataStoreConnectionSignals data_store_connection_signals = 35 [(google.api.field_behavior) = OPTIONAL]; } // Represents the natural language text to be processed. message TextInput { // Required. The UTF-8 encoded natural language text to be processed. string text = 1 [(google.api.field_behavior) = REQUIRED]; } // Represents the intent to trigger programmatically rather than as a result of // natural language processing. message IntentInput { // Required. The unique identifier of the intent. // Format: `projects//locations//agents//intents/`. string intent = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "dialogflow.googleapis.com/Intent" } ]; } // Represents the natural speech audio to be processed. message AudioInput { // Required. Instructs the speech recognizer how to process the speech audio. InputAudioConfig config = 1 [(google.api.field_behavior) = REQUIRED]; // The natural language speech audio to be processed. // A single request can contain up to 2 minutes of speech audio data. // The [transcribed // text][google.cloud.dialogflow.cx.v3beta1.QueryResult.transcript] cannot // contain more than 256 bytes. // // For non-streaming audio detect intent, both `config` and `audio` must be // provided. // For streaming audio detect intent, `config` must be provided in // the first request and `audio` must be provided in all following requests. bytes audio = 2; } // Represents the event to trigger. message EventInput { // Name of the event. string event = 1; } // Represents the input for dtmf event. message DtmfInput { // The dtmf digits. string digits = 1; // The finish digit (if any). string finish_digit = 2; } // Represents one match result of [MatchIntent][]. message Match { // Type of a Match. enum MatchType { // Not specified. Should never be used. MATCH_TYPE_UNSPECIFIED = 0; // The query was matched to an intent. INTENT = 1; // The query directly triggered an intent. DIRECT_INTENT = 2; // The query was used for parameter filling. PARAMETER_FILLING = 3; // No match was found for the query. NO_MATCH = 4; // Indicates an empty query. NO_INPUT = 5; // The query directly triggered an event. EVENT = 6; // The query was matched to a Knowledge Connector answer. KNOWLEDGE_CONNECTOR = 8; // The query was handled by a // [`Playbook`][google.cloud.dialogflow.cx.v3beta1.Playbook]. PLAYBOOK = 9; } // The [Intent][google.cloud.dialogflow.cx.v3beta1.Intent] that matched the // query. Some, not all fields are filled in this message, including but not // limited to: `name` and `display_name`. Only filled for // [`INTENT`][google.cloud.dialogflow.cx.v3beta1.Match.MatchType] match type. Intent intent = 1; // The event that matched the query. Filled for // [`EVENT`][google.cloud.dialogflow.cx.v3beta1.Match.MatchType], // [`NO_MATCH`][google.cloud.dialogflow.cx.v3beta1.Match.MatchType] and // [`NO_INPUT`][google.cloud.dialogflow.cx.v3beta1.Match.MatchType] match // types. string event = 6; // The collection of parameters extracted from the query. // // Depending on your protocol or client library language, this is a // map, associative array, symbol table, dictionary, or JSON object // composed of a collection of (MapKey, MapValue) pairs: // // * MapKey type: string // * MapKey value: parameter name // * MapValue type: If parameter's entity type is a composite entity then use // map, otherwise, depending on the parameter value type, it could be one of // string, number, boolean, null, list or map. // * MapValue value: If parameter's entity type is a composite entity then use // map from composite entity property names to property values, otherwise, // use parameter value. google.protobuf.Struct parameters = 2; // Final text input which was matched during MatchIntent. This value can be // different from original input sent in request because of spelling // correction or other processing. string resolved_input = 3; // Type of this [Match][google.cloud.dialogflow.cx.v3beta1.Match]. MatchType match_type = 4; // The confidence of this match. Values range from 0.0 (completely uncertain) // to 1.0 (completely certain). // This value is for informational purpose only and is only used to help match // the best intent within the classification threshold. This value may change // for the same end-user expression at any time due to a model retraining or // change in implementation. float confidence = 5; } // Request of [MatchIntent][]. message MatchIntentRequest { // Required. The name of the session this query is sent to. // Format: `projects//locations//agents//sessions/` or `projects//locations//agents//environments//sessions/`. // If `Environment ID` is not specified, we assume default 'draft' // environment. // It's up to the API caller to choose an appropriate `Session ID`. It can be // a random number or some type of session identifiers (preferably hashed). // The length of the `Session ID` must not exceed 36 characters. // // For more information, see the [sessions // guide](https://cloud.google.com/dialogflow/cx/docs/concept/session). string session = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "dialogflow.googleapis.com/Session" } ]; // The parameters of this query. QueryParameters query_params = 2; // Required. The input specification. QueryInput query_input = 3 [(google.api.field_behavior) = REQUIRED]; // Persist session parameter changes from `query_params`. bool persist_parameter_changes = 5; } // Response of [MatchIntent][]. message MatchIntentResponse { // The original conversational query. oneof query { // If [natural language text][google.cloud.dialogflow.cx.v3beta1.TextInput] // was provided as input, this field will contain a copy of the text. string text = 1; // If an [intent][google.cloud.dialogflow.cx.v3beta1.IntentInput] was // provided as input, this field will contain a copy of the intent // identifier. Format: `projects//locations//agents//intents/`. string trigger_intent = 2 [(google.api.resource_reference) = { type: "dialogflow.googleapis.com/Intent" }]; // If [natural language speech // audio][google.cloud.dialogflow.cx.v3beta1.AudioInput] was provided as // input, this field will contain the transcript for the audio. string transcript = 3; // If an [event][google.cloud.dialogflow.cx.v3beta1.EventInput] was provided // as input, this field will contain a copy of the event name. string trigger_event = 6; } // Match results, if more than one, ordered descendingly by the confidence // we have that the particular intent matches the query. repeated Match matches = 4; // The current [Page][google.cloud.dialogflow.cx.v3beta1.Page]. Some, not all // fields are filled in this message, including but not limited to `name` and // `display_name`. Page current_page = 5; } // Request of [FulfillIntent][] message FulfillIntentRequest { // Must be same as the corresponding MatchIntent request, otherwise the // behavior is undefined. MatchIntentRequest match_intent_request = 1; // The matched intent/event to fulfill. Match match = 2; // Instructs the speech synthesizer how to generate output audio. OutputAudioConfig output_audio_config = 3; } // Response of [FulfillIntent][] message FulfillIntentResponse { // Output only. The unique identifier of the response. It can be used to // locate a response in the training example set or for reporting issues. string response_id = 1; // The result of the conversational query. QueryResult query_result = 2; // The audio data bytes encoded as specified in the request. // Note: The output audio is generated based on the values of default platform // text responses found in the // [`query_result.response_messages`][google.cloud.dialogflow.cx.v3beta1.QueryResult.response_messages] // field. If multiple default text responses exist, they will be concatenated // when generating audio. If no default platform text responses exist, the // generated audio content will be empty. // // In some scenarios, multiple output audio fields may be present in the // response structure. In these cases, only the top-most-level audio output // has content. bytes output_audio = 3; // The config used by the speech synthesizer to generate the output audio. OutputAudioConfig output_audio_config = 4; } // 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. message SentimentAnalysisResult { // Sentiment score between -1.0 (negative sentiment) and 1.0 (positive // sentiment). float score = 1; // A non-negative number in the [0, +inf) range, which represents the absolute // magnitude of sentiment, regardless of score (positive or negative). float magnitude = 2; }