from langchain.text_splitter import RecursiveCharacterTextSplitter
from sentence_transformers import SentenceTransformer
from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
from langchain_community.embeddings import HuggingFaceEmbeddings
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=500, chunk_overlap=20)
    text_chunks=text_splitter.split_documents(extracted_data)
    return text_chunks



#Download the Embeddings from HuggingFace 
def download_hugging_face_embeddings():
    try:
        print("Starting to load embedding model...")
        embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
        print("Embedding model loaded successfully")
        return embeddings
    except Exception as e:
        print(f"Error loading embedding model: {e}")
        raise