`langchain_community.document_loaders.pdf`.PyPDFLoader¶

class langchain_community.document_loaders.pdf.PyPDFLoader(file_path: str, password: Optional[Union[str, bytes]] = None, headers: Optional[Dict] = None, extract_images: bool = False, *, extraction_mode: str = 'plain', extraction_kwargs: Optional[Dict] = 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-pasword",
    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 (Optional[Union[str, bytes]]) –
headers (Optional[Dict]) –
extract_images (bool) –
extraction_mode (str) –
extraction_kwargs (Optional[Dict]) –

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

Initialize with a file path.

Parameters

file_path (str) –
password (Optional[Union[str, bytes]]) –
headers (Optional[Dict]) –
extract_images (bool) –
extraction_mode (str) –
extraction_kwargs (Optional[Dict]) –

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: 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 PyPDFLoader¶

langchain_community.document_loaders.pdf.PyPDFLoader¶

Examples using PyPDFLoader¶

`langchain_community.document_loaders.pdf`.PyPDFLoader¶