pdfextractor.py

import PyPDF2
import io
import os
from dotenv import load_dotenv
import groq
import streamlit as st
from typing import List, Dict, Optional
from pydantic import BaseModel

load_dotenv()

def extract_text_from_pdf(pdf_path):
    """
    Extracts text from a PDF file.

    Args:
        pdf_path (str): The path to the PDF file.

    Returns:
        str: The extracted text.  Returns an empty string if extraction fails.
    """
    text = ""
    try:
        with open(pdf_path, 'rb') as file:
            reader = PyPDF2.PdfReader(file)
            for page_num in range(len(reader.pages)):
                page = reader.pages[page_num]
                text += page.extract_text()
    except Exception as e:
        print(f"Error extracting text from PDF: {e}")
        return ""  # Return empty string on failure

    return text