app.py

import os
import pickle
import numpy as np
import gradio as gr
import fitz  # PyMuPDF
from docx import Document
from transformers import AutoModel, AutoTokenizer
import faiss
import torch

# =============================================
# EMBEDDING MODEL SETUP
# =============================================
model_name = "sentence-transformers/all-MiniLM-L6-v2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
embedding_model = AutoModel.from_pretrained(model_name)

def get_embeddings(texts):
    if isinstance(texts, str):
        texts = [texts]
    inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="pt", max_length=512)
    with torch.no_grad():
        outputs = embedding_model(**inputs)
    return outputs.last_hidden_state[:, 0].cpu().numpy()

# =============================================
# DOCUMENT STORAGE SETUP
# =============================================
index_path = "faiss_index.pkl"
document_texts_path = "document_texts.pkl"
document_texts = []

embedding_dim = 384  # Dimension for all-MiniLM-L6-v2
if os.path.exists(index_path) and os.path.exists(document_texts_path):
    try:
        with open(index_path, "rb") as f:
            index = pickle.load(f)
        with open(document_texts_path, "rb") as f:
            document_texts = pickle.load(f)
    except Exception as e:
        print(f"Error loading index: {e}")
        index = faiss.IndexFlatIP(embedding_dim)
else:
    index = faiss.IndexFlatIP(embedding_dim)

# =============================================
# DOCUMENT PROCESSING FUNCTIONS
# =============================================
def extract_text_from_pdf(pdf_path):
    text = ""
    try:
        doc = fitz.open(pdf_path)
        for page in doc:
            text += page.get_text()
    except Exception as e:
        print(f"PDF error: {e}")
    return text

def extract_text_from_docx(docx_path):
    text = ""
    try:
        doc = Document(docx_path)
        text = "\n".join([para.text for para in doc.paragraphs])
    except Exception as e:
        print