preprocess.py

from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import UnstructuredAPIFileLoader


def load_documents_OCR(file_path, unstructured_api):
    """Load documents that require OCR via unstructured."""
    loader = UnstructuredAPIFileLoader(file_path=file_path, api_key=unstructured_api,mode='paged')
    documents = loader.load()
    return documents


def load_documents(file_path):
    """Load documents using LangChain."""
    loader = PyPDFLoader(file_path)
    documents = loader.load()
    return documents

def split_documents(documents):
    """Split documents using LangChain splitter."""
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=500)
    split_docs = text_splitter.split_documents(documents)
    return split_docs


def load_and_split_documents(file_path):
    """Load and split documents from the specified file path."""
    loader = PyPDFLoader(file_path)
    documents = loader.load()
    if not documents:
        print("No documents loaded from file:", file_path)
        return []
    split_docs = split_documents(documents)
    if not split_docs:
        print("Document splitting resulted in no output for file:", file_path)
    return split_docs

def update_metadata(documents, original_name):
    """Update metadata for each document."""
    updated_documents = []
    for doc in documents:
        doc.metadata['source'] = original_name
        updated_documents.append(doc)
    return updated_documents