langchain_community.document_loaders.image_captions.ImageCaptionLoader¶

class langchain_community.document_loaders.image_captions.ImageCaptionLoader(images: Union[str, bytes, List[Union[str, bytes]]], blip_processor: str = 'Salesforce/blip-image-captioning-base', blip_model: str = 'Salesforce/blip-image-captioning-base')[source]¶

Load image captions.

By default, the loader utilizes the pre-trained Salesforce BLIP image captioning model. https://huggingface.co/Salesforce/blip-image-captioning-base

Initialize with a list of image data (bytes) or file paths

Parameters

  • images (Union[str, bytes, List[Union[str, bytes]]]) – Either a single image or a list of images. Accepts image data (bytes) or file paths to images.

  • blip_processor (str) – The name of the pre-trained BLIP processor.

  • blip_model (str) – The name of the pre-trained BLIP model.

Methods

__init__(images[, blip_processor, blip_model])

Initialize with a list of image data (bytes) or file paths

alazy_load()

A lazy loader for Documents.

lazy_load()

A lazy loader for Documents.

load()

Load from a list of image data or file paths

load_and_split([text_splitter])

Load Documents and split into chunks.
__init__(images: Union[str, bytes, List[Union[str, bytes]]], blip_processor: str = 'Salesforce/blip-image-captioning-base', blip_model: str = 'Salesforce/blip-image-captioning-base')[source]¶

Initialize with a list of image data (bytes) or file paths

Parameters

  • images (Union[str, bytes, List[Union[str, bytes]]]) – Either a single image or a list of images. Accepts image data (bytes) or file paths to images.

  • blip_processor (str) – The name of the pre-trained BLIP processor.

  • blip_model (str) – The name of the pre-trained BLIP model.

async alazy_load() → AsyncIterator[Document]¶

A lazy loader for Documents.

Return type

AsyncIterator[Document]

lazy_load() → Iterator[Document]¶

A lazy loader for Documents.

Return type

Iterator[Document]

load() → List[Document][source]¶

Load from a list of image data or file paths

Return type

List[Document]

load_and_split(text_splitter: Optional[TextSplitter] = None) → List[Document]¶

Load Documents and split into chunks. Chunks are returned as Documents.

Do not override this method. It should be considered to be deprecated!

Parameters

text_splitter (Optional[TextSplitter]) – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.

Returns

List of Documents.

Return type

List[Document]

Examples using ImageCaptionLoader¶