Coba Gemini 1.5 Pro, model multimodal kami yang paling canggih di Vertex AI, dan lihat apa yang dapat Anda bangun dengan jendela konteks token 1 juta. Coba Gemini 1.5 Pro, model multimodal kami yang paling canggih di Vertex AI, dan lihat apa yang dapat Anda bangun dengan jendela konteks token 1 juta.

Mendeteksi intent

Ada contoh dasar yang menunjukkan cara mendeteksi intent di quickstart. Panduan ini memberikan contoh tambahan untuk skenario lanjutan.

Mendeteksi intent dengan input audio

Contoh berikut menunjukkan cara mendeteksi intent dengan input audio.

Java

Untuk mengautentikasi ke Dialogflow, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, baca Menyiapkan autentikasi untuk lingkungan pengembangan lokal.


import com.google.api.gax.rpc.ApiException;
import com.google.cloud.dialogflow.cx.v3.AudioEncoding;
import com.google.cloud.dialogflow.cx.v3.AudioInput;
import com.google.cloud.dialogflow.cx.v3.DetectIntentRequest;
import com.google.cloud.dialogflow.cx.v3.DetectIntentResponse;
import com.google.cloud.dialogflow.cx.v3.InputAudioConfig;
import com.google.cloud.dialogflow.cx.v3.QueryInput;
import com.google.cloud.dialogflow.cx.v3.QueryResult;
import com.google.cloud.dialogflow.cx.v3.SessionName;
import com.google.cloud.dialogflow.cx.v3.SessionsClient;
import com.google.cloud.dialogflow.cx.v3.SessionsSettings;
import com.google.protobuf.ByteString;
import java.io.FileInputStream;
import java.io.IOException;

public class DetectIntentAudioInput {

  // DialogFlow API Detect Intent sample with Audio input.
  public static void main(String[] args) throws IOException, ApiException {
    /** TODO (developer): replace these values with your own values */
    String projectId = "my-project-id";
    String locationId = "global";
    String agentId = "my-agent-id";
    String audioFileName = "resources/book_a_room.wav";
    int sampleRateHertz = 16000;
    /*
     * A session ID is a string of at most 36 bytes in size.
     * Your system is responsible for generating unique session IDs.
     * They can be random numbers, hashed end-user identifiers,
     * or any other values that are convenient for you to generate.
     */
    String sessionId = "my-UUID";
    String languageCode = "en";

    detectIntent(
        projectId, locationId, agentId, audioFileName, sampleRateHertz, sessionId, languageCode);
  }

  public static void detectIntent(
      String projectId,
      String locationId,
      String agentId,
      String audioFileName,
      int sampleRateHertz,
      String sessionId,
      String languageCode)
      throws IOException, ApiException {

    SessionsSettings.Builder sessionsSettingsBuilder = SessionsSettings.newBuilder();
    if (locationId.equals("global")) {
      sessionsSettingsBuilder.setEndpoint("dialogflow.googleapis.com:443");
    } else {
      sessionsSettingsBuilder.setEndpoint(locationId + "-dialogflow.googleapis.com:443");
    }
    SessionsSettings sessionsSettings = sessionsSettingsBuilder.build();

    // Instantiates a client by setting the session name.
    // Format:`projects/<ProjectID>/locations/<LocationID>/agents/<AgentID>/sessions/<SessionID>`

    // Note: close() needs to be called on the SessionsClient object to clean up resources
    // such as threads. In the example below, try-with-resources is used,
    // which automatically calls close().
    try (SessionsClient sessionsClient = SessionsClient.create(sessionsSettings)) {
      SessionName session =
          SessionName.ofProjectLocationAgentSessionName(projectId, locationId, agentId, sessionId);

      // TODO : Uncomment if you want to print session path
      // System.out.println("Session Path: " + session.toString());
      InputAudioConfig inputAudioConfig =
          InputAudioConfig.newBuilder()
              .setAudioEncoding(AudioEncoding.AUDIO_ENCODING_LINEAR_16)
              .setSampleRateHertz(sampleRateHertz)
              .build();

      try (FileInputStream audioStream = new FileInputStream(audioFileName)) {
        // Subsequent requests must **only** contain the audio data.
        // Following messages: audio chunks. We just read the file in fixed-size chunks. In reality
        // you would split the user input by time.
        byte[] buffer = new byte[4096];
        int bytes = audioStream.read(buffer);
        AudioInput audioInput =
            AudioInput.newBuilder()
                .setAudio(ByteString.copyFrom(buffer, 0, bytes))
                .setConfig(inputAudioConfig)
                .build();
        QueryInput queryInput =
            QueryInput.newBuilder()
                .setAudio(audioInput)
                .setLanguageCode("en-US") // languageCode = "en-US"
                .build();

        DetectIntentRequest request =
            DetectIntentRequest.newBuilder()
                .setSession(session.toString())
                .setQueryInput(queryInput)
                .build();

        // Performs the detect intent request.
        DetectIntentResponse response = sessionsClient.detectIntent(request);

        // Display the query result.
        QueryResult queryResult = response.getQueryResult();

        System.out.println("====================");
        System.out.format(
            "Detected Intent: %s (confidence: %f)\n",
            queryResult.getTranscript(), queryResult.getIntentDetectionConfidence());
      }
    }
  }
}

Node.js

Untuk mengautentikasi ke Dialogflow, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, baca Menyiapkan autentikasi untuk lingkungan pengembangan lokal.

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'my-project';
// const location = 'global';
// const agentId = 'my-agent';
// const audioFileName = '/path/to/audio.raw';
// const encoding = 'AUDIO_ENCODING_LINEAR_16';
// const sampleRateHertz = 16000;
// const languageCode = 'en'

// Imports the Google Cloud Some API library
const {SessionsClient} = require('@google-cloud/dialogflow-cx');
/**
 * Example for regional endpoint:
 *   const location = 'us-central1'
 *   const client = new SessionsClient({apiEndpoint: 'us-central1-dialogflow.googleapis.com'})
 */
const client = new SessionsClient();

const fs = require('fs');
const util = require('util');

async function detectIntentAudio() {
  const sessionId = Math.random().toString(36).substring(7);
  const sessionPath = client.projectLocationAgentSessionPath(
    projectId,
    location,
    agentId,
    sessionId
  );
  console.info(sessionPath);

  // Read the content of the audio file and send it as part of the request.
  const readFile = util.promisify(fs.readFile);
  const inputAudio = await readFile(audioFileName);

  const request = {
    session: sessionPath,
    queryInput: {
      audio: {
        config: {
          audioEncoding: encoding,
          sampleRateHertz: sampleRateHertz,
        },
        audio: inputAudio,
      },
      languageCode,
    },
  };
  const [response] = await client.detectIntent(request);
  console.log(`User Query: ${response.queryResult.transcript}`);
  for (const message of response.queryResult.responseMessages) {
    if (message.text) {
      console.log(`Agent Response: ${message.text.text}`);
    }
  }
  if (response.queryResult.match.intent) {
    console.log(
      `Matched Intent: ${response.queryResult.match.intent.displayName}`
    );
  }
  console.log(
    `Current Page: ${response.queryResult.currentPage.displayName}`
  );
}

detectIntentAudio();

Python

Untuk mengautentikasi ke Dialogflow, siapkan Kredensial Default Aplikasi. Untuk mengetahui informasi selengkapnya, baca Menyiapkan autentikasi untuk lingkungan pengembangan lokal.

def run_sample():
    # TODO(developer): Replace these values when running the function
    project_id = "YOUR-PROJECT-ID"
    # For more information about regionalization see https://cloud.google.com/dialogflow/cx/docs/how/region
    location_id = "YOUR-LOCATION-ID"
    # For more info on agents see https://cloud.google.com/dialogflow/cx/docs/concept/agent
    agent_id = "YOUR-AGENT-ID"
    agent = f"projects/{project_id}/locations/{location_id}/agents/{agent_id}"
    # For more information on sessions see https://cloud.google.com/dialogflow/cx/docs/concept/session
    session_id = str(uuid.uuid4())
    audio_file_path = "YOUR-AUDIO-FILE-PATH"
    # For more supported languages see https://cloud.google.com/dialogflow/es/docs/reference/language
    language_code = "en-us"

    detect_intent_audio(agent, session_id, audio_file_path, language_code)

def detect_intent_audio(agent, session_id, audio_file_path, language_code):
    """Returns the result of detect intent with an audio file as input.

    Using the same `session_id` between requests allows continuation
    of the conversation."""
    session_path = f"{agent}/sessions/{session_id}"
    print(f"Session path: {session_path}\n")
    client_options = None
    agent_components = AgentsClient.parse_agent_path(agent)
    location_id = agent_components["location"]
    if location_id != "global":
        api_endpoint = f"{location_id}-dialogflow.googleapis.com:443"
        print(f"API Endpoint: {api_endpoint}\n")
        client_options = {"api_endpoint": api_endpoint}
    session_client = SessionsClient(client_options=client_options)

    input_audio_config = audio_config.InputAudioConfig(
        audio_encoding=audio_config.AudioEncoding.AUDIO_ENCODING_LINEAR_16,
        sample_rate_hertz=24000,
    )

    with open(audio_file_path, "rb") as audio_file:
        input_audio = audio_file.read()

    audio_input = session.AudioInput(config=input_audio_config, audio=input_audio)
    query_input = session.QueryInput(audio=audio_input, language_code=language_code)
    request = session.DetectIntentRequest(session=session_path, query_input=query_input)
    response = session_client.detect_intent(request=request)

    print("=" * 20)
    print(f"Query text: {response.query_result.transcript}")
    response_messages = [
        " ".join(msg.text.text) for msg in response.query_result.response_messages
    ]
    print(f"Response text: {' '.join(response_messages)}\n")