PyPDFLoader#

class langchain_community.document_loaders.pdf.PyPDFLoader(file_path: str, password: str | bytes | None = None, headers: Dict | None = None, extract_images: bool = False, *, extraction_mode: str = 'plain', extraction_kwargs: Dict | None = None)[source]#

PyPDFLoader document loader integration

Setup:

Install langchain-community.

pip install -U langchain-community

Instantiate:

from langchain_community.document_loaders import PyPDFLoader

loader = PyPDFLoader(
    file_path = "./example_data/layout-parser-paper.pdf",
    password = "my-password",
    extract_images = True,
    # headers = None
    # extraction_mode = "plain",
    # extraction_kwargs = None,
)

Lazy load:

docs = []
docs_lazy = loader.lazy_load()

# async variant:
# docs_lazy = await loader.alazy_load()

for doc in docs_lazy:
    docs.append(doc)
print(docs[0].page_content[:100])
print(docs[0].metadata)

LayoutParser : A Uniﬁed Toolkit for Deep
Learning Based Document Image Analysis
Zejiang Shen1( ), R
{'source': './example_data/layout-parser-paper.pdf', 'page': 0}

Async load:

docs = await loader.aload()
print(docs[0].page_content[:100])
print(docs[0].metadata)

LayoutParser : A Uniﬁed Toolkit for Deep
Learning Based Document Image Analysis
Zejiang Shen1( ), R
{'source': './example_data/layout-parser-paper.pdf', 'page': 0}

Initialize with a file path.

Attributes

source

Methods

`__init__`(file_path[, password, headers, ...])	Initialize with a file path.
`alazy_load`()	A lazy loader for Documents.
`aload`()	Load data into Document objects.
`lazy_load`()	Lazy load given path as pages.
`load`()	Load data into Document objects.
`load_and_split`([text_splitter])	Load Documents and split into chunks.

Parameters:

file_path (str)
password (str | bytes | None)
headers (Dict | None)
extract_images (bool)
extraction_mode (str)
extraction_kwargs (Dict | None)

__init__(file_path: str, password: str | bytes | None = None, headers: Dict | None = None, extract_images: bool = False, *, extraction_mode: str = 'plain', extraction_kwargs: Dict | None = None) → None[source]#

Initialize with a file path.

Parameters:

file_path (str)
password (str | bytes | None)
headers (Dict | None)
extract_images (bool)
extraction_mode (str)
extraction_kwargs (Dict | None)

Return type:

None

async alazy_load() → AsyncIterator[Document]#

A lazy loader for Documents.

Return type:: AsyncIterator[Document]

async aload() → list[Document]#

Load data into Document objects.

Return type:: list[Document]

lazy_load() → Iterator[Document][source]#

Lazy load given path as pages.

Return type:: Iterator[Document]

load() → list[Document]#

Load data into Document objects.

Return type:: list[Document]

load_and_split(text_splitter: TextSplitter | None = 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 PyPDFLoader