File

DocxLoader

Bases: BaseLoader

Microsoft Word (Docx) loader.

load_data

load_data(input_file: str, **kwargs: Any) -> list[Document]

Loads data from the specified file.

Attributes:

Name	Type	Description
input_file	str	File path to load.

Returns:

Type	Description
list[Document]	list[Document]: A list of Document objects loaded from the file.

HTMLLoader

Bases: BaseLoader

Load a HTML file and extract text from a specific tag.

Attributes:

Name	Type	Description
tag	str	HTML tag to extract. Defaults to section.

load_data

load_data(input_file: str, **kwargs: Any) -> list[Document]

Loads data from the specified file.

Parameters:

Name	Type	Description	Default
input_file	str	File path to load.	required

Returns:

Type	Description
list[Document]	list[Document]: A list of Document objects loaded from the file.

JSONLoader

Bases: BaseLoader

JSON loader.

Attributes:

Name	Type	Description
jq_schema	str	jq schema to use to extract the data from the JSON.

load_data

load_data(input_file: str, **kwargs: Any) -> list[Document]

Loads data from the specified file.

Parameters:

Name	Type	Description	Default
input_file	str	File path to load.	required

Returns:

Type	Description
list[Document]	list[Document]: A list of Document objects loaded from the file.

PDFLoader

Bases: BaseLoader

PDF loader using PyPDF.

load_data

load_data(input_file: str, **kwargs: Any) -> list[Document]

Loads data from the specified file.

Attributes:

Name	Type	Description
input_file	str	File path to load.

Returns:

Type	Description
list[Document]	list[Document]: A list of Document objects loaded from the file.