Vision Language

final image = ImageInput.file('/path/to/photo.jpg');

final result = await RunAnywhere.vlm.generate(image, 'What is in this photo?');
print(result.text);

ImageInput.file('/path/to/photo.jpg');       // read by path
ImageInput.bytes(pngOrJpegBytes);            // encoded bytes
ImageInput.rawRgb(rgbBytes, width, height);  // tightly packed RGB8

await for (final event in RunAnywhere.vlm.generateStream(image, 'Describe this')) {
  switch (event) {
    case GenerationToken(:final text):
      setState(() => _caption += text);
    case GenerationCompleted(:final result):
      debugPrint('${result.outputTokens} tokens');
    default:
      break;
  }
}

final result = await RunAnywhere.vlm.generate(
  image,
  'Read the text in this image.',
  options: LlmOptions(maxOutputTokens: 512, temperature: 0.2),
);

await RunAnywhere.models.register(
  ModelRegistration.archive(
    id: 'smolvlm-500m-instruct-q8_0',
    name: 'SmolVLM 500M Instruct',
    url: 'https://example.com/smolvlm-500m-instruct-q8_0.tar.gz',
    archiveType: ArchiveType.ARCHIVE_TYPE_TAR_GZ,
    structure: ArchiveStructure.ARCHIVE_STRUCTURE_NESTED_DIRECTORY,
    framework: InferenceFramework.INFERENCE_FRAMEWORK_LLAMA_CPP,
    category: ModelCategory.MODEL_CATEGORY_MULTIMODAL,
    memoryRequirementBytes: 900000000,
  ),
);