app.py

from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import gradio as gr
import tempfile
import os
import csv

# Initialize the processor and model
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")

def generate_image_caption(image):
    """
    Generate a caption for the given image.

    Args:
        image (PIL.Image): The image object.

    Returns:
        str: The generated caption.
    """
    image = image.convert("RGB")
    inputs = processor(images=image, return_tensors="pt")
    outputs = model.generate(**inputs)
    caption = processor.decode(outputs[0], skip_special_tokens=True)
    return caption

def generate_keywords(caption):
    """
    Generate a list of keywords from the caption, focusing on SEO relevance.

    Args:
        caption (str): The image caption.

    Returns:
        list: A list of 50 single-word keywords.
    """
    words = caption.split()
    # Remove common stopwords and keep unique words for SEO relevance
    stopwords = {"a", "the", "and", "of", "in", "on", "with", "at", "for", "to", "is"}
    keywords = list(set(word.lower() for word in words if word.lower() not in stopwords))
    
    # Ensure the list contains exactly 50 keywords (add repetitions if needed)
    if len(keywords) > 50:
        keywords = keywords[:50]
    elif len(keywords) < 50:
        keywords.extend(keywords[:50-len(keywords)])
    
    return keywords

def process_images(image_files):
    """
    Process uploaded images to generate metadata and create a CSV file.

    Args:
        image_files (list of file-like objects): List of uploaded image files.

    Returns:
        tuple: A list of PIL images, path to the CSV file.
    """
    metadata = []
    temp_dir = tempfile.mkdtemp()

    for image_file in image_files:
        filename = os.path.basename(image_file.name)
        image = Image.open(image_file)
        caption = generate_image_caption(image)
        if caption:
            keywords = generate_keywords(caption)
            title = caption if 70 <= len(caption) <= 100 else caption[:100]
            metadata.append({
                'filename': filename,
                'title': title,
                'keywords': keywords
            })

    # Create CSV file
    csv_file_path = os.path.join(temp_dir, 'images_metadata.csv')
    with open(csv_file_path, mode='w', newline='', encoding='utf-8') as file:
        writer = csv.writer(file)
        writer.writerow(['Filename', 'Title', 'Keywords'])
        for data in metadata:
            filename = data['filename']
            title = data['title']
            keywords = ','.join(data['keywords'])
            writer.writerow([filename, title, keywords])

    return [Image.open(image_file.name) for image_file in image_files], csv_file_path

# Define Gradio interface
iface = gr.Interface(
    fn=process_images,
    inputs=[
        gr.Files(label="Upload Image Files")  # Use gr.Files for multiple file uploads
    ],
    outputs=[
        gr.Gallery(label="Processed Images"),
        gr.File(label="Download Metadata CSV")
    ],
    title="Image Captioning and Metadata Generator",
    description="Upload multiple images to generate captions and metadata. Download the metadata as a CSV file."
)

# Launch the interface
iface.launch(debug=True)