インテリジェントな Android アプリを構築する: オンデバイス推論

// implementation("com.google.mlkit:genai-prompt:1.0.0-beta3")
// ksp("com.google.mlkit:genai-schema-compiler:1.0.0-alpha1")

@Generable("Information extracted from an expense receipt")
data class ParsedReceipt(
  @Guide("Generated title for the expense less than 6 words. Based on restaurant or activity name.")
  val title: String,
  @Guide("Total amount of the expense. Look for values at the bottom and words like total or balance due.")
  val amount: Double,
  @Guide("Type of expense", enumValues = ["travel", "food", "shopping", "entertainment", "other"])
  val category: String,
)

val prompt = "Determine if the image is a receipt or expense. 
    If it is NOT a receipt or expense, output the text 'NOT_A_RECEIPT'.
    Otherwise, parse the receipt information."

val request = generateContentRequest(ImagePart(bitmap), TextPart(prompt)) {}
val requestWithStructuredOutput = generateTypedContentRequest(request, ParsedReceipt::class)

// Define the configuration for Gemini Nano 4 E4B preview model  
// When selecting models, you can specify which performance charactertists are most important
//  for your use case. Use ModelPreference.FULL when you want to prioritize reasoning power over speed. 
//  Use ModelPreference.FAST when complex logic is not required and latency is a priority.
val previewFullConfig = generationConfig {
    modelConfig = modelConfig {
        releaseStage = ModelReleaseStage.PREVIEW
        preference = ModelPreference.FULL
    }
}

val geminiNano4BPreviewModel = Generation.getClient(previewFullConfig)
val response = geminiNano4BPreviewModel.generateContent(requestWithStructuredOutput)
val parsedReceipt: ParsedReceipt? = response.candidates.firstOrNull()?.response

// implementation("com.google.mlkit:genai-prompt:1.0.0-beta3")
// implementation("com.google.mlkit:genai-speech-recognition:1.0.0-alpha1")

val tripEvents = ... 

// Set up speech recognition
val speechRecognizerOptions =
    speechRecognizerOptions {
        locale = Locale.US
        preferredMode = SpeechRecognizerOptions.Mode.MODE_ADVANCED
    }
val speechRecognizer: SpeechRecognizer = SpeechRecognition.getClient(speechRecognizerOptions)

suspend fun transcribeVoiceNote(recognizer: SpeechRecognizer) {
    // Display partial text as the user is recording audio
    var partialTextResponse = ""

    // Display the full text once user is finished recording audio
    var transcription = ""

    val request: SpeechRecognizerRequest
        = speechRecognizerRequest { audioSource = AudioSource.fromMic() }
    recognizer.startRecognition(request).collect { response ->
        when (response) {
            is SpeechRecognizerResponse.PartialTextResponse -> {
                partialTextResponse = response.text
            }
            is SpeechRecognizerResponse.FinalTextResponse -> {
                transcription = response.text
                processAndCategorizeVoiceNote(transcription, tripEvents)
            }
        }
    }
}

fun processAndCategorizeVoiceNote(transcribedVoiceNote: String, events: List<Event>) {
    val prompt = "Given the voice note $transcribedVoiceNote
     and the following events for this trip: $events, rewrite this transcription
     to remove filler words. Then, identify which events from the
     list this rewritten transcription matches to."

     // Utilize ML Kit's Prompt API to process voice note and tag it with the relevant trip activities
     Generation.getClient().generateContent(prompt)
}

Copyright 2026 Google LLC.
SPDX-License-Identifier: Apache-2.0