Module base

BaseImageToText

class BaseImageToText(BaseComponent)

Abstract class for ImageToText.

BaseImageToText.generate_captions

@abstractmethod
def generate_captions(image_file_paths: List[str],
                      generation_kwargs: Optional[dict] = None,
                      batch_size: Optional[int] = None) -> List[Document]

Abstract method for generating captions.

Arguments:

• image_file_paths: Paths to the images for which you want to generate captions.
• generation_kwargs: Dictionary containing arguments for the generate() method of the Hugging Face model. See generate() on Hugging Face.
• batch_size: Number of images to process at a time.

Returns:

List of Documents. Document.content is the caption. Document.meta["image_file_path"] contains the path to the image file.

BaseImageToText.run

def run(file_paths: Optional[List[str]] = None,
        documents: Optional[List[Document]] = None)

Arguments:

• file_paths: Paths to the images for which you want to generate captions.
• documents: List of image Documents to process into text.

BaseImageToText.run_batch

def run_batch(file_paths: Optional[List[str]] = None,
              documents: Optional[List[Document]] = None)

Arguments:

• file_paths: Paths to the images for which you want to generate captions.
• documents: List of image Documents to process into text.