Build an AI Photo Caption Generator for Android

suspend fun loadScaled(context: Context, uri: Uri, maxSide: Int = 1024): Bitmap =
    withContext(Dispatchers.IO) {
        val source = ImageDecoder.createSource(context.contentResolver, uri)
        ImageDecoder.decodeBitmap(source) { decoder, info, _ ->
            val (w, h) = info.size.width to info.size.height
            val scale = maxSide.toFloat() / maxOf(w, h)
            if (scale < 1f) decoder.setTargetSize((w * scale).toInt(), (h * scale).toInt())
            decoder.allocator = ImageDecoder.ALLOCATOR_SOFTWARE
        }
    }

@Serializable
data class CaptionResult(val captions: List<String>, val altText: String)

class CaptionGenerator(private val json: Json = Json { ignoreUnknownKeys = true }) {

    private val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
        modelName = "gemini-3.8-flash",                                   // check current models
        generationConfig = generationConfig {
            responseMimeType = "application/json"
            responseSchema = Schema.obj(
                mapOf(
                    "captions" to Schema.array(Schema.string()),
                    "altText" to Schema.string(),
                )
            )
            temperature = 0.8f
        },
    )

    suspend fun generate(image: Bitmap, tone: Tone): CaptionResult {
        val response = model.generateContent(content {
            image(image)
            text(
                "Write 3 short social media captions for this photo in a ${tone.label} tone " +
                "(max 120 characters each, at most 2 hashtags). Also write factual alt text " +
                "(max 150 characters) describing what is visible. Don't guess identities of people."
            )
        })
        val result = json.decodeFromString<CaptionResult>(response.text ?: error("Empty response"))
        return result.copy(
            captions = result.captions.map { it.take(150).trim() }.filter { it.isNotEmpty() }.take(3),
            altText = result.altText.take(200).trim(),
        )
    }
}

enum class Tone(val label: String) { FUN("fun"), PROFESSIONAL("professional"), POETIC("poetic"), MINIMAL("minimal") }

@Composable
fun CaptionOptions(result: CaptionResult, onShare: (String) -> Unit) {
    var selected by rememberSaveable { mutableIntStateOf(0) }
    var edited by rememberSaveable(selected) { mutableStateOf(result.captions.getOrElse(selected) { "" }) }

    Column(verticalArrangement = Arrangement.spacedBy(8.dp)) {
        Text("AI suggestions. Review before posting.", style = MaterialTheme.typography.labelMedium)
        result.captions.forEachIndexed { i, caption ->
            FilterChip(selected = i == selected, onClick = { selected = i }, label = { Text(caption, maxLines = 2) })
        }
        OutlinedTextField(value = edited, onValueChange = { edited = it }, label = { Text("Caption") })
        Text("Alt text: ${result.altText}", style = MaterialTheme.typography.bodySmall)
        Button(onClick = { onShare(edited) }) { Text("Share") }
    }
}