Skip to content

Commit d7d604f

Browse files
yoshi-automationjkwlui
yoshi-automation
authored and
jkwlui
committed
feat: add the updateDocument and reloadDocument` methods (#315)
* [CHANGE ME] Re-generated to pick up changes in the API or client library generator. * fix(protos): sync latest proto backfilled with missing methods * update Kokoro configs
1 parent 85a62cf commit d7d604f

24 files changed

Lines changed: 1330 additions & 656 deletions

‎packages/google-cloud-dialogflow/protos/google/cloud/dialogflow/v2/audio_config.proto‎

Lines changed: 124 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -27,6 +27,129 @@ option java_outer_classname = "AudioConfigProto";
2727
option java_package = "com.google.cloud.dialogflow.v2";
2828
option objc_class_prefix = "DF";
2929

30+
// Audio encoding of the audio content sent in the conversational query request.
31+
// Refer to the
32+
// [Cloud Speech API
33+
// documentation](https://cloud.google.com/speech-to-text/docs/basics) for more
34+
// details.
35+
enum AudioEncoding {
36+
// Not specified.
37+
AUDIO_ENCODING_UNSPECIFIED = 0;
38+
39+
// Uncompressed 16-bit signed little-endian samples (Linear PCM).
40+
AUDIO_ENCODING_LINEAR_16 = 1;
41+
42+
// [`FLAC`](https://xiph.org/flac/documentation.html) (Free Lossless Audio
43+
// Codec) is the recommended encoding because it is lossless (therefore
44+
// recognition is not compromised) and requires only about half the
45+
// bandwidth of `LINEAR16`. `FLAC` stream encoding supports 16-bit and
46+
// 24-bit samples, however, not all fields in `STREAMINFO` are supported.
47+
AUDIO_ENCODING_FLAC = 2;
48+
49+
// 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
50+
AUDIO_ENCODING_MULAW = 3;
51+
52+
// Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
53+
AUDIO_ENCODING_AMR = 4;
54+
55+
// Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
56+
AUDIO_ENCODING_AMR_WB = 5;
57+
58+
// Opus encoded audio frames in Ogg container
59+
// ([OggOpus](https://wiki.xiph.org/OggOpus)).
60+
// `sample_rate_hertz` must be 16000.
61+
AUDIO_ENCODING_OGG_OPUS = 6;
62+
63+
// Although the use of lossy encodings is not recommended, if a very low
64+
// bitrate encoding is required, `OGG_OPUS` is highly preferred over
65+
// Speex encoding. The [Speex](https://speex.org/) encoding supported by
66+
// Dialogflow API has a header byte in each block, as in MIME type
67+
// `audio/x-speex-with-header-byte`.
68+
// It is a variant of the RTP Speex encoding defined in
69+
// [RFC 5574](https://tools.ietf.org/html/rfc5574).
70+
// The stream is a sequence of blocks, one block per RTP packet. Each block
71+
// starts with a byte containing the length of the block, in bytes, followed
72+
// by one or more frames of Speex data, padded to an integral number of
73+
// bytes (octets) as specified in RFC 5574. In other words, each RTP header
74+
// is replaced with a single byte containing the block length. Only Speex
75+
// wideband is supported. `sample_rate_hertz` must be 16000.
76+
AUDIO_ENCODING_SPEEX_WITH_HEADER_BYTE = 7;
77+
}
78+
79+
// Variant of the specified [Speech model][google.cloud.dialogflow.v2.InputAudioConfig.model] to use.
80+
//
81+
// See the [Cloud Speech
82+
// documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
83+
// for which models have different variants. For example, the "phone_call" model
84+
// has both a standard and an enhanced variant. When you use an enhanced model,
85+
// you will generally receive higher quality results than for a standard model.
86+
enum SpeechModelVariant {
87+
// No model variant specified. In this case Dialogflow defaults to
88+
// USE_BEST_AVAILABLE.
89+
SPEECH_MODEL_VARIANT_UNSPECIFIED = 0;
90+
91+
// Use the best available variant of the [Speech
92+
// model][InputAudioConfig.model] that the caller is eligible for.
93+
//
94+
// Please see the [Dialogflow
95+
// docs](https://cloud.google.com/dialogflow-enterprise/docs/data-logging) for
96+
// how to make your project eligible for enhanced models.
97+
USE_BEST_AVAILABLE = 1;
98+
99+
// Use standard model variant even if an enhanced model is available. See the
100+
// [Cloud Speech
101+
// documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
102+
// for details about enhanced models.
103+
USE_STANDARD = 2;
104+
105+
// Use an enhanced model variant:
106+
//
107+
// * If an enhanced variant does not exist for the given
108+
// [model][google.cloud.dialogflow.v2.InputAudioConfig.model] and request language, Dialogflow falls
109+
// back to the standard variant.
110+
//
111+
// The [Cloud Speech
112+
// documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
113+
// describes which models have enhanced variants.
114+
//
115+
// * If the API caller isn't eligible for enhanced models, Dialogflow returns
116+
// an error. Please see the [Dialogflow
117+
// docs](https://cloud.google.com/dialogflow-enterprise/docs/data-logging)
118+
// for how to make your project eligible.
119+
USE_ENHANCED = 3;
120+
}
121+
122+
// Instructs the speech recognizer how to process the audio content.
123+
message InputAudioConfig {
124+
// Required. Audio encoding of the audio content to process.
125+
AudioEncoding audio_encoding = 1;
126+
127+
// Required. Sample rate (in Hertz) of the audio content sent in the query.
128+
// Refer to
129+
// [Cloud Speech API
130+
// documentation](https://cloud.google.com/speech-to-text/docs/basics) for
131+
// more details.
132+
int32 sample_rate_hertz = 2;
133+
134+
// Required. The language of the supplied audio. Dialogflow does not do
135+
// translations. See [Language
136+
// Support](https://cloud.google.com/dialogflow-enterprise/docs/reference/language)
137+
// for a list of the currently supported language codes. Note that queries in
138+
// the same session do not necessarily need to specify the same language.
139+
string language_code = 3;
140+
141+
// Optional. The collection of phrase hints which are used to boost accuracy
142+
// of speech recognition.
143+
// Refer to
144+
// [Cloud Speech API
145+
// documentation](https://cloud.google.com/speech-to-text/docs/basics#phrase-hints)
146+
// for more details.
147+
repeated string phrase_hints = 4;
148+
149+
// Optional. Which variant of the [Speech model][google.cloud.dialogflow.v2.InputAudioConfig.model] to use.
150+
SpeechModelVariant model_variant = 10;
151+
}
152+
30153
// Gender of the voice as described in
31154
// [SSML voice element](https://www.w3.org/TR/speech-synthesis11/#edef_voice).
32155
enum SsmlVoiceGender {
@@ -109,7 +232,7 @@ enum OutputAudioEncoding {
109232
OUTPUT_AUDIO_ENCODING_OGG_OPUS = 3;
110233
}
111234

112-
// Instructs the speech synthesizer how to generate the output audio content.
235+
// Instructs the speech synthesizer on how to generate the output audio content.
113236
message OutputAudioConfig {
114237
// Required. Audio encoding of the synthesized audio content.
115238
OutputAudioEncoding audio_encoding = 1;

‎packages/google-cloud-dialogflow/protos/google/cloud/dialogflow/v2/session.proto‎

Lines changed: 0 additions & 77 deletions
Original file line numberDiff line numberDiff line change
@@ -418,34 +418,6 @@ message StreamingRecognitionResult {
418418
float confidence = 4;
419419
}
420420

421-
// Instructs the speech recognizer how to process the audio content.
422-
message InputAudioConfig {
423-
// Required. Audio encoding of the audio content to process.
424-
AudioEncoding audio_encoding = 1;
425-
426-
// Required. Sample rate (in Hertz) of the audio content sent in the query.
427-
// Refer to
428-
// [Cloud Speech API
429-
// documentation](https://cloud.google.com/speech-to-text/docs/basics) for
430-
// more details.
431-
int32 sample_rate_hertz = 2;
432-
433-
// Required. The language of the supplied audio. Dialogflow does not do
434-
// translations. See [Language
435-
// Support](https://cloud.google.com/dialogflow-enterprise/docs/reference/language)
436-
// for a list of the currently supported language codes. Note that queries in
437-
// the same session do not necessarily need to specify the same language.
438-
string language_code = 3;
439-
440-
// Optional. The collection of phrase hints which are used to boost accuracy
441-
// of speech recognition.
442-
// Refer to
443-
// [Cloud Speech API
444-
// documentation](https://cloud.google.com/speech-to-text/docs/basics#phrase-hints)
445-
// for more details.
446-
repeated string phrase_hints = 4;
447-
}
448-
449421
// Represents the natural language text to be processed.
450422
message TextInput {
451423
// Required. The UTF-8 encoded natural language text to be processed.
@@ -478,55 +450,6 @@ message EventInput {
478450
string language_code = 3;
479451
}
480452

481-
// Audio encoding of the audio content sent in the conversational query request.
482-
// Refer to the
483-
// [Cloud Speech API
484-
// documentation](https://cloud.google.com/speech-to-text/docs/basics) for more
485-
// details.
486-
enum AudioEncoding {
487-
// Not specified.
488-
AUDIO_ENCODING_UNSPECIFIED = 0;
489-
490-
// Uncompressed 16-bit signed little-endian samples (Linear PCM).
491-
AUDIO_ENCODING_LINEAR_16 = 1;
492-
493-
// [`FLAC`](https://xiph.org/flac/documentation.html) (Free Lossless Audio
494-
// Codec) is the recommended encoding because it is lossless (therefore
495-
// recognition is not compromised) and requires only about half the
496-
// bandwidth of `LINEAR16`. `FLAC` stream encoding supports 16-bit and
497-
// 24-bit samples, however, not all fields in `STREAMINFO` are supported.
498-
AUDIO_ENCODING_FLAC = 2;
499-
500-
// 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
501-
AUDIO_ENCODING_MULAW = 3;
502-
503-
// Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
504-
AUDIO_ENCODING_AMR = 4;
505-
506-
// Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
507-
AUDIO_ENCODING_AMR_WB = 5;
508-
509-
// Opus encoded audio frames in Ogg container
510-
// ([OggOpus](https://wiki.xiph.org/OggOpus)).
511-
// `sample_rate_hertz` must be 16000.
512-
AUDIO_ENCODING_OGG_OPUS = 6;
513-
514-
// Although the use of lossy encodings is not recommended, if a very low
515-
// bitrate encoding is required, `OGG_OPUS` is highly preferred over
516-
// Speex encoding. The [Speex](https://speex.org/) encoding supported by
517-
// Dialogflow API has a header byte in each block, as in MIME type
518-
// `audio/x-speex-with-header-byte`.
519-
// It is a variant of the RTP Speex encoding defined in
520-
// [RFC 5574](https://tools.ietf.org/html/rfc5574).
521-
// The stream is a sequence of blocks, one block per RTP packet. Each block
522-
// starts with a byte containing the length of the block, in bytes, followed
523-
// by one or more frames of Speex data, padded to an integral number of
524-
// bytes (octets) as specified in RFC 5574. In other words, each RTP header
525-
// is replaced with a single byte containing the block length. Only Speex
526-
// wideband is supported. `sample_rate_hertz` must be 16000.
527-
AUDIO_ENCODING_SPEEX_WITH_HEADER_BYTE = 7;
528-
}
529-
530453
// Configures the types of sentiment analysis to perform.
531454
message SentimentAnalysisRequestConfig {
532455
// Optional. Instructs the service to perform sentiment analysis on

‎packages/google-cloud-dialogflow/protos/google/cloud/dialogflow/v2beta1/audio_config.proto‎

Lines changed: 47 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -76,7 +76,50 @@ enum AudioEncoding {
7676
AUDIO_ENCODING_SPEEX_WITH_HEADER_BYTE = 7;
7777
}
7878

79-
// Instructs the speech recognizer how to process the audio content.
79+
// Variant of the specified [Speech model][google.cloud.dialogflow.v2beta1.InputAudioConfig.model] to use.
80+
//
81+
// See the [Cloud Speech
82+
// documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
83+
// for which models have different variants. For example, the "phone_call" model
84+
// has both a standard and an enhanced variant. When you use an enhanced model,
85+
// you will generally receive higher quality results than for a standard model.
86+
enum SpeechModelVariant {
87+
// No model variant specified. In this case Dialogflow defaults to
88+
// USE_BEST_AVAILABLE.
89+
SPEECH_MODEL_VARIANT_UNSPECIFIED = 0;
90+
91+
// Use the best available variant of the [Speech
92+
// model][InputAudioConfig.model] that the caller is eligible for.
93+
//
94+
// Please see the [Dialogflow
95+
// docs](https://cloud.google.com/dialogflow-enterprise/docs/data-logging) for
96+
// how to make your project eligible for enhanced models.
97+
USE_BEST_AVAILABLE = 1;
98+
99+
// Use standard model variant even if an enhanced model is available. See the
100+
// [Cloud Speech
101+
// documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
102+
// for details about enhanced models.
103+
USE_STANDARD = 2;
104+
105+
// Use an enhanced model variant:
106+
//
107+
// * If an enhanced variant does not exist for the given
108+
// [model][google.cloud.dialogflow.v2beta1.InputAudioConfig.model] and request language, Dialogflow falls
109+
// back to the standard variant.
110+
//
111+
// The [Cloud Speech
112+
// documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
113+
// describes which models have enhanced variants.
114+
//
115+
// * If the API caller isn't eligible for enhanced models, Dialogflow returns
116+
// an error. Please see the [Dialogflow
117+
// docs](https://cloud.google.com/dialogflow-enterprise/docs/data-logging)
118+
// for how to make your project eligible.
119+
USE_ENHANCED = 3;
120+
}
121+
122+
// Instructs the speech recognizer on how to process the audio content.
80123
message InputAudioConfig {
81124
// Required. Audio encoding of the audio content to process.
82125
AudioEncoding audio_encoding = 1;
@@ -115,6 +158,9 @@ message InputAudioConfig {
115158
// documentation](https://cloud.google.com/speech-to-text/docs/basics#select-model)
116159
// for more details.
117160
string model = 7;
161+
162+
// Optional. Which variant of the [Speech model][google.cloud.dialogflow.v2beta1.InputAudioConfig.model] to use.
163+
SpeechModelVariant model_variant = 10;
118164
}
119165

120166
// Gender of the voice as described in

0 commit comments

Comments
 (0)
⚡