feat: added conversation process config, ImportDocument and SuggestSm…

…artReplies API

PiperOrigin-RevId: 423223164

google/cloud/dialogflow/v2/audio_config.proto

@@ -16,11 +16,11 @@ syntax = "proto3";
 
 package google.cloud.dialogflow.v2;
 
+import "google/api/annotations.proto";
 import "google/api/field_behavior.proto";
 import "google/api/resource.proto";
 import "google/protobuf/duration.proto";
 import "google/protobuf/timestamp.proto";
-import "google/api/annotations.proto";
 
 option cc_enable_arenas = true;
 option csharp_namespace = "Google.Cloud.Dialogflow.V2";
@@ -109,31 +109,6 @@ message SpeechContext {
   float boost = 2;
 }
 
-// Information for a word recognized by the speech recognizer.
-message SpeechWordInfo {
-  // The word this info is for.
-  string word = 3;
-
-  // Time offset relative to the beginning of the audio that corresponds to the
-  // start of the spoken word. This is an experimental feature and the accuracy
-  // of the time offset can vary.
-  google.protobuf.Duration start_offset = 1;
-
-  // Time offset relative to the beginning of the audio that corresponds to the
-  // end of the spoken word. This is an experimental feature and the accuracy of
-  // the time offset can vary.
-  google.protobuf.Duration end_offset = 2;
-
-  // The Speech confidence between 0.0 and 1.0 for this word. A higher number
-  // indicates an estimated greater likelihood that the recognized word is
-  // correct. The default of 0.0 is a sentinel value indicating that confidence
-  // was not set.
-  //
-  // This field is not guaranteed to be fully stable over time for the same
-  // audio input. Users should also not rely on it to always be provided.
-  float confidence = 4;
-}
-
 // Variant of the specified [Speech model][google.cloud.dialogflow.v2.InputAudioConfig.model] to use.
 //
 // See the [Cloud Speech
@@ -177,6 +152,31 @@ enum SpeechModelVariant {
   USE_ENHANCED = 3;
 }
 
+// Information for a word recognized by the speech recognizer.
+message SpeechWordInfo {
+  // The word this info is for.
+  string word = 3;
+
+  // Time offset relative to the beginning of the audio that corresponds to the
+  // start of the spoken word. This is an experimental feature and the accuracy
+  // of the time offset can vary.
+  google.protobuf.Duration start_offset = 1;
+
+  // Time offset relative to the beginning of the audio that corresponds to the
+  // end of the spoken word. This is an experimental feature and the accuracy of
+  // the time offset can vary.
+  google.protobuf.Duration end_offset = 2;
+
+  // The Speech confidence between 0.0 and 1.0 for this word. A higher number
+  // indicates an estimated greater likelihood that the recognized word is
+  // correct. The default of 0.0 is a sentinel value indicating that confidence
+  // was not set.
+  //
+  // This field is not guaranteed to be fully stable over time for the same
+  // audio input. Users should also not rely on it to always be provided.
+  float confidence = 4;
+}
+
 // Instructs the speech recognizer how to process the audio content.
 message InputAudioConfig {
   // Required. Audio encoding of the audio content to process.
@@ -256,6 +256,23 @@ message InputAudioConfig {
   bool disable_no_speech_recognized_event = 14;
 }
 
+// Gender of the voice as described in
+// [SSML voice element](https://www.w3.org/TR/speech-synthesis11/#edef_voice).
+enum SsmlVoiceGender {
+  // An unspecified gender, which means that the client doesn't care which
+  // gender the selected voice will have.
+  SSML_VOICE_GENDER_UNSPECIFIED = 0;
+
+  // A male voice.
+  SSML_VOICE_GENDER_MALE = 1;
+
+  // A female voice.
+  SSML_VOICE_GENDER_FEMALE = 2;
+
+  // A gender-neutral voice.
+  SSML_VOICE_GENDER_NEUTRAL = 3;
+}
+
 // Description of which voice to use for speech synthesis.
 message VoiceSelectionParams {
   // Optional. The name of the voice. If not set, the service will choose a
@@ -303,21 +320,29 @@ message SynthesizeSpeechConfig {
   VoiceSelectionParams voice = 4;
 }
 
-// Gender of the voice as described in
-// [SSML voice element](https://www.w3.org/TR/speech-synthesis11/#edef_voice).
-enum SsmlVoiceGender {
-  // An unspecified gender, which means that the client doesn't care which
-  // gender the selected voice will have.
-  SSML_VOICE_GENDER_UNSPECIFIED = 0;
+// Audio encoding of the output audio format in Text-To-Speech.
+enum OutputAudioEncoding {
+  // Not specified.
+  OUTPUT_AUDIO_ENCODING_UNSPECIFIED = 0;
 
-  // A male voice.
-  SSML_VOICE_GENDER_MALE = 1;
+  // Uncompressed 16-bit signed little-endian samples (Linear PCM).
+  // Audio content returned as LINEAR16 also contains a WAV header.
+  OUTPUT_AUDIO_ENCODING_LINEAR_16 = 1;
 
-  // A female voice.
-  SSML_VOICE_GENDER_FEMALE = 2;
+  // MP3 audio at 32kbps.
+  OUTPUT_AUDIO_ENCODING_MP3 = 2;
 
-  // A gender-neutral voice.
-  SSML_VOICE_GENDER_NEUTRAL = 3;
+  // MP3 audio at 64kbps.
+  OUTPUT_AUDIO_ENCODING_MP3_64_KBPS = 4;
+
+  // Opus encoded audio wrapped in an ogg container. The result will be a
+  // file which can be played natively on Android, and in browsers (at least
+  // Chrome and Firefox). The quality of the encoding is considerably higher
+  // than MP3 while using approximately the same bitrate.
+  OUTPUT_AUDIO_ENCODING_OGG_OPUS = 3;
+
+  // 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
+  OUTPUT_AUDIO_ENCODING_MULAW = 5;
 }
 
 // Instructs the speech synthesizer on how to generate the output audio content.
@@ -349,28 +374,3 @@ message SpeechToTextConfig {
   // would emit an error.
   SpeechModelVariant speech_model_variant = 1;
 }
-
-// Audio encoding of the output audio format in Text-To-Speech.
-enum OutputAudioEncoding {
-  // Not specified.
-  OUTPUT_AUDIO_ENCODING_UNSPECIFIED = 0;
-
-  // Uncompressed 16-bit signed little-endian samples (Linear PCM).
-  // Audio content returned as LINEAR16 also contains a WAV header.
-  OUTPUT_AUDIO_ENCODING_LINEAR_16 = 1;
-
-  // MP3 audio at 32kbps.
-  OUTPUT_AUDIO_ENCODING_MP3 = 2;
-
-  // MP3 audio at 64kbps.
-  OUTPUT_AUDIO_ENCODING_MP3_64_KBPS = 4;
-
-  // Opus encoded audio wrapped in an ogg container. The result will be a
-  // file which can be played natively on Android, and in browsers (at least
-  // Chrome and Firefox). The quality of the encoding is considerably higher
-  // than MP3 while using approximately the same bitrate.
-  OUTPUT_AUDIO_ENCODING_OGG_OPUS = 3;
-
-  // 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
-  OUTPUT_AUDIO_ENCODING_MULAW = 5;
-}

google/cloud/dialogflow/v2/conversation.proto

@@ -20,6 +20,8 @@ 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/v2/audio_config.proto";
+import "google/cloud/dialogflow/v2/conversation_profile.proto";
 import "google/cloud/dialogflow/v2/participant.proto";
 import "google/protobuf/empty.proto";
 import "google/protobuf/timestamp.proto";

google/cloud/dialogflow/v2/conversation_event.proto

@@ -16,9 +16,9 @@ syntax = "proto3";
 
 package google.cloud.dialogflow.v2;
 
+import "google/api/annotations.proto";
 import "google/cloud/dialogflow/v2/participant.proto";
 import "google/rpc/status.proto";
-import "google/api/annotations.proto";
 
 option cc_enable_arenas = true;
 option csharp_namespace = "Google.Cloud.Dialogflow.V2";

google/cloud/dialogflow/v2/conversation_profile.proto

@@ -329,6 +329,9 @@ message HumanAgentAssistantConfig {
 
     // Configs of custom conversation model.
     ConversationModelConfig conversation_model_config = 7;
+
+    // Configs for processing conversation.
+    ConversationProcessConfig conversation_process_config = 8;
   }
 
   // Detail human agent assistant config.
@@ -469,6 +472,13 @@ message HumanAgentAssistantConfig {
                       }];
   }
 
+  // Config to process conversation.
+  message ConversationProcessConfig {
+    // Number of recent non-small-talk sentences to use as context for article
+    // and FAQ suggestion
+    int32 recent_sentences_count = 2;
+  }
+
   // Configuration for analyses to run on each conversation message.
   message MessageAnalysisConfig {
     // Enable entity extraction in conversation messages on [agent assist

google/cloud/dialogflow/v2/dialogflow_v2.yaml

@@ -26,6 +26,7 @@ types:
 - name: google.cloud.dialogflow.v2.ConversationEvent
 - name: google.cloud.dialogflow.v2.ExportAgentResponse
 - name: google.cloud.dialogflow.v2.HumanAgentAssistantEvent
+- name: google.cloud.dialogflow.v2.ImportDocumentsResponse
 - name: google.cloud.dialogflow.v2.KnowledgeOperationMetadata
 - name: google.cloud.dialogflow.v2.OriginalDetectIntentRequest
 - name: google.cloud.dialogflow.v2.WebhookRequest

google/cloud/dialogflow/v2/document.proto

@@ -97,6 +97,31 @@ service Documents {
     };
   }
 
+  // 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](https://cloud.google.com/dialogflow/cx/docs/how/long-running-operation).
+  // The returned `Operation` type has the following method-specific fields:
+  //
+  // - `metadata`: [KnowledgeOperationMetadata][google.cloud.dialogflow.v2.KnowledgeOperationMetadata]
+  // - `response`: [ImportDocumentsResponse][google.cloud.dialogflow.v2.ImportDocumentsResponse]
+  rpc ImportDocuments(ImportDocumentsRequest) returns (google.longrunning.Operation) {
+    option (google.api.http) = {
+      post: "/v2/{parent=projects/*/knowledgeBases/*}/documents:import"
+      body: "*"
+      additional_bindings {
+        post: "/v2/{parent=projects/*/locations/*/knowledgeBases/*}/documents:import"
+        body: "*"
+      }
+    };
+    option (google.longrunning.operation_info) = {
+      response_type: "ImportDocumentsResponse"
+      metadata_type: "KnowledgeOperationMetadata"
+    };
+  }
+
   // Deletes the specified document.
   //
   // This method is a [long-running
@@ -224,17 +249,6 @@ message Document {
     pattern: "projects/{project}/locations/{location}/knowledgeBases/{knowledge_base}/documents/{document}"
   };
 
-  // The status of a reload attempt.
-  message ReloadStatus {
-    // The time of a reload attempt.
-    // This reload may have been triggered automatically or manually and may
-    // not have succeeded.
-    google.protobuf.Timestamp time = 1;
-
-    // The status of a reload attempt or the initial load.
-    google.rpc.Status status = 2;
-  }
-
   // The knowledge type of document content.
   enum KnowledgeType {
     // The type is unspecified or arbitrary.
@@ -258,6 +272,17 @@ message Document {
     ARTICLE_SUGGESTION = 3;
   }
 
+  // The status of a reload attempt.
+  message ReloadStatus {
+    // The time of a reload attempt.
+    // This reload may have been triggered automatically or manually and may
+    // not have succeeded.
+    google.protobuf.Timestamp time = 1;
+
+    // The status of a reload attempt or the initial load.
+    google.rpc.Status status = 2;
+  }
+
   // Optional. The document resource name.
   // The name must be empty when creating a document.
   // Format: `projects/<Project ID>/locations/<Location
@@ -404,6 +429,65 @@ message CreateDocumentRequest {
   Document document = 2 [(google.api.field_behavior) = REQUIRED];
 }
 
+// Request message for [Documents.ImportDocuments][google.cloud.dialogflow.v2.Documents.ImportDocuments].
+message ImportDocumentsRequest {
+  // Required. The knowledge base to import documents into.
+  // Format: `projects/<Project ID>/locations/<Location
+  // ID>/knowledgeBases/<Knowledge Base ID>`.
+  string parent = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      child_type: "dialogflow.googleapis.com/Document"
+    }
+  ];
+
+  // Required. The source to use for importing documents.
+  //
+  // If the source captures multiple objects, then multiple documents will be
+  // created, one corresponding to each object, and all of these documents will
+  // be created using the same document template.
+  //
+  // Dialogflow supports up to 350 documents in each request. If you try to
+  // import more, Dialogflow will return an error.
+  oneof source {
+    // The Google Cloud Storage location for the documents.
+    // The path can include a wildcard.
+    //
+    // These URIs may have the forms
+    // `gs://<bucket-name>/<object-name>`.
+    // `gs://<bucket-name>/<object-path>/*.<extension>`.
+    GcsSources gcs_source = 2;
+  }
+
+  // Required. Document template used for importing all the documents.
+  ImportDocumentTemplate document_template = 3 [(google.api.field_behavior) = REQUIRED];
+
+  // Whether to import custom metadata from Google Cloud Storage.
+  // Only valid when the document source is Google Cloud Storage URI.
+  bool import_gcs_custom_metadata = 4;
+}
+
+// The template used for importing documents.
+message ImportDocumentTemplate {
+  // Required. The MIME type of the document.
+  string mime_type = 1 [(google.api.field_behavior) = REQUIRED];
+
+  // Required. The knowledge type of document content.
+  repeated Document.KnowledgeType knowledge_types = 2 [(google.api.field_behavior) = REQUIRED];
+
+  // Metadata for the document. The metadata supports arbitrary
+  // key-value pairs. Suggested use cases include storing a document's title,
+  // an external URL distinct from the document's content_uri, etc.
+  // The max size of a `key` or a `value` of the metadata is 1024 bytes.
+  map<string, string> metadata = 3;
+}
+
+// Response message for [Documents.ImportDocuments][google.cloud.dialogflow.v2.Documents.ImportDocuments].
+message ImportDocumentsResponse {
+  // Includes details about skipped documents or any other warnings.
+  repeated google.rpc.Status warnings = 1;
+}
+
 // Request message for [Documents.DeleteDocument][google.cloud.dialogflow.v2.Documents.DeleteDocument].
 message DeleteDocumentRequest {
   // Required. The name of the document to delete.
@@ -507,4 +591,7 @@ message KnowledgeOperationMetadata {
 
   // Output only. The current state of this operation.
   State state = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // The name of the knowledge base interacted with during the operation.
+  string knowledge_base = 3;
 }