langchain_community.document_loaders.pdf
.PyPDFDirectoryLoader¶
- class langchain_community.document_loaders.pdf.PyPDFDirectoryLoader(path: str, glob: str = '**/[!.]*.pdf', silent_errors: bool = False, load_hidden: bool = False, recursive: bool = False, extract_images: bool = False)[source]¶
Load a directory with PDF files using pypdf and chunks at character level.
Loader also stores page numbers in metadata.
Methods
__init__
(path[, glob, silent_errors, ...])A lazy loader for Documents.
A lazy loader for Documents.
load
()Load data into Document objects.
load_and_split
([text_splitter])Load Documents and split into chunks.
- Parameters
path (str) –
glob (str) –
silent_errors (bool) –
load_hidden (bool) –
recursive (bool) –
extract_images (bool) –
- __init__(path: str, glob: str = '**/[!.]*.pdf', silent_errors: bool = False, load_hidden: bool = False, recursive: bool = False, extract_images: bool = False)[source]¶
- Parameters
path (str) –
glob (str) –
silent_errors (bool) –
load_hidden (bool) –
recursive (bool) –
extract_images (bool) –
- async alazy_load() AsyncIterator[Document] ¶
A lazy loader for Documents.
- Return type
AsyncIterator[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]