QwenVisionAssetAnalyzer#

class rapidtools.processing.QwenVisionAssetAnalyzer(prompt: str | Path = '', model_id: str = 'Qwen/Qwen3.5-4B', device: str = 'auto', load_in_4bit: bool = False, temperature: float = 0.4, max_tokens: int = 512, max_images_per_asset: int = 2, batch_size: int = 1, image_filter: Callable[[ImageAsset], bool] | None = None, cancel_event: Event | None = None, attribute_prefix: str | None = None)[source]#

Bases: HFVisionAssetAnalyzer

Deprecated: use AssetAnalyzer(load('qwen_vl', ...)). Prefix qwen_vl_.

MODEL_CLASS#

alias of QwenVisionInference

ATTRIBUTE_PREFIX: str | None = 'qwen_vl'#

Default attribute prefix when neither the model nor the caller gives one.