preprocessing/__init__.py

# Preprocessing package

from .preprocessing import DocumentPreprocessor
from .preprocessing_modules import (
    PDFDownloader,
    TextExtractor,
    TextChunker,
    EmbeddingManager,
    VectorStorage,
    MetadataManager,
    ModularDocumentPreprocessor
)

__all__ = [
    'DocumentPreprocessor',
    'PDFDownloader',
    'TextExtractor',
    'TextChunker', 
    'EmbeddingManager',
    'VectorStorage',
    'MetadataManager',
    'ModularDocumentPreprocessor'
]