owlapy.agen_kg.text_loader

Text loading module for extracting text from various file formats. Supports: TXT, PDF, DOCX, RTF, HTML, and raw text strings.

Also provides text chunking utilities for handling large documents that may not fit in an LLM’s context window.

Attributes

logger

Classes

`TextLoader`	Base class for text loaders.
`TXTLoader`	Loader for plain text files.
`PDFLoader`	Loader for PDF files.
`DOCXLoader`	Loader for DOCX files.
`RTFLoader`	Loader for RTF files.
`HTMLLoader`	Loader for HTML files.
`RawTextLoader`	Loader for raw text strings.
`UniversalTextLoader`	Universal text loader that automatically detects file type and loads content.

Module Contents

owlapy.agen_kg.text_loader.logger

class owlapy.agen_kg.text_loader.TextLoader[source]

Bases: abc.ABC

Base class for text loaders.

abstractmethod load(source: str | pathlib.Path) → str[source]

Load text from the given source.

Parameters:: source – File path or raw text string.
Returns:: Extracted text content.
Raises:: ValueError – If the source is invalid or cannot be processed.

class owlapy.agen_kg.text_loader.TXTLoader[source]

Bases: TextLoader

Loader for plain text files.

load(source: str | pathlib.Path) → str[source]: Load text from a .txt file.

class owlapy.agen_kg.text_loader.PDFLoader[source]

Bases: TextLoader

Loader for PDF files.

load(source: str | pathlib.Path) → str[source]: Load text from a PDF file.

class owlapy.agen_kg.text_loader.DOCXLoader[source]

Bases: TextLoader

Loader for DOCX files.

load(source: str | pathlib.Path) → str[source]: Load text from a DOCX file.

class owlapy.agen_kg.text_loader.RTFLoader[source]

Bases: TextLoader

Loader for RTF files.

load(source: str | pathlib.Path) → str[source]: Load text from an RTF file.

class owlapy.agen_kg.text_loader.HTMLLoader[source]

Bases: TextLoader

Loader for HTML files.

load(source: str | pathlib.Path) → str[source]: Load text from an HTML file.

class owlapy.agen_kg.text_loader.RawTextLoader[source]

Bases: TextLoader

Loader for raw text strings.

load(source: str | pathlib.Path) → str[source]: Return the source as-is if it’s not a file.

class owlapy.agen_kg.text_loader.UniversalTextLoader(enable_logging: bool = False)[source]

Universal text loader that automatically detects file type and loads content. Handles multiple formats: TXT, PDF, DOCX, RTF, HTML, and raw text strings.

logging = False

loaders

load(source: str | pathlib.Path, file_type: str | None = None) → str[source]

Load text from various sources.

Parameters:

source – File path (str or Path), or raw text string.
file_type – Optional file extension (e.g., ‘.pdf’, ‘.txt’). If not provided, will be auto-detected from the source.

Returns:

Extracted text content.

Raises:

ValueError – If the file type is not supported or content cannot be extracted.
FileNotFoundError – If the specified file does not exist.

supports_file_type(file_type: str) → bool[source]

Check if a file type is supported.

Parameters:: file_type – File extension (e.g., ‘.pdf’, ‘pdf’).
Returns:: True if the file type is supported, False otherwise.

property supported_formats: list: Get list of supported file formats.