src/helpers.py

from langchain_community.document_loaders import TextLoader, PyPDFLoader, DirectoryLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_huggingface import HuggingFaceEmbeddings


#Extract Data From the PDF File
def load_pdf_file(data):
    loader= DirectoryLoader(data,
                            glob="*.pdf",
                            loader_cls=PyPDFLoader)

    documents=loader.load()

    return documents


#Split the Data into Text Chunks
def text_split(extracted_data):
    text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
    text_chunks=text_splitter.split_documents(extracted_data)
    return text_chunks




#Download the Embeddings from Hugging Face
def download_hugging_face_embeddings():
    embeddings=HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
    return embeddings