#Extract text and image metadata from the PDF document
text_metadata_df, image_metadata_df = get_document_metadata(
    multimodal_model,  # we are passing gemini 1.0 pro vision model
    pdf_folder_path,
    image_save_dir="images",
    image_description_prompt=image_description_prompt,
    embedding_size=1408,
)

print("\n\n --- Completed processing. ---")

import fitz
import os
from PIL import Image


def get_image_for_gemini(
    doc: fitz.Document,
    image: tuple,
    image_no: int,
    image_save_dir: str,
    file_name: str,
    page_num: int,
) -> Tuple[Image, str]:
    """
    Extracts an image from a PDF document, converts it to JPEG format, saves it to a specified directory,
    and loads it as a PIL Image Object.

    Parameters:
    - doc (fitz.Document): The PDF document from which the image is extracted.
    - image (tuple): A tuple containing image information.
    - image_no (int): The image number for naming purposes.
    - image_save_dir (str): The directory where the image will be saved.
    - file_name (str): The base name for the image file.
    - page_num (int): The page number from which the image is extracted.

    Returns:
    - Tuple[Image.Image, str]: A tuple containing the Gemini Image object and the image filename.
    """

    # Extract the image from the document
    xref = image[0]
    pix = fitz.Pixmap(doc, xref)

    # Convert the image to JPEG format
    pix.tobytes("jpeg")

    # Create the image file name
    image_name = f"{image_save_dir}/{file_name}_image_{page_num}_{image_no}_{xref}.jpeg"

    # Create the image save directory if it doesn't exist
    os.makedirs(image_save_dir, exist_ok=True)

    # Save the image to the specified location
    pix.save(image_name)

    # Load the saved image as a Gemini Image Object
    image_for_gemini = Image.load_from_file(image_name)

    return image_for_gemini, image_name