app.py

import openai
import gradio as gr
import os

# Set your OpenAI API Key
openai.api_key = "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"  # Replace with your API key

def generate_caption(image):
    """Generate a caption for the uploaded image using OpenAI's GPT-4 Vision API."""
    with open(image, "rb") as img_file:
        response = openai.chat.completions.create(
            model="gpt-4-turbo",
            messages=[
                {
                    "role": "system",
                    "content": "You are an AI assistant that describes images accurately."
                },
                {
                    "role": "user",
                    "content": [
                        {"type": "text", "text": "Describe the contents of this image in detail."},
                        {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64," + img_file.read().decode()}},
                    ],
                },
            ],
            max_tokens=100
        )

    caption = response.choices[0].message.content
    return caption

# Gradio UI
iface = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type="filepath"),
    outputs="text",
    title="Image Captioning App",
    description="Upload an image, and the AI will generate a descriptive caption."
)

# Run the app
if __name__ == "__main__":
    iface.launch()