from sentence_transformers import SentenceTransformer
from preprocess import preprocess_books
import pickle
import pandas as pd
def extract_sbert_embeddings(df, save_path="model/sbert_embeddings2.pkl"):
    """Extracts BERT embeddings from book summaries."""
    model = SentenceTransformer('all-mpnet-base-v2')  
    # Generate embeddings for book summaries
    embeddings = model.encode(df["combined_text"].fillna(""), show_progress_bar=True)

    with open(save_path, "wb") as f:
        pickle.dump(embeddings, f)

    return embeddings

def load_book_data(filepath="data/books_summary_cleaned.csv"):
    """Loads book dataset and ensures necessary columns exist."""
    df = pd.read_csv(filepath)
    

    return df
# preprocess_books()
# df = load_book_data()
# embeddings = extract_sbert_embeddings(df)