app.py

import base64
import requests
from io import BytesIO
from PIL import Image
import gradio as gr

def encode_image(img):
    """
    Encodes a PIL Image to a base64 string.
    """
    buffered = BytesIO()
    img.save(buffered, format="PNG")
    encoded_string = base64.b64encode(buffered.getvalue()).decode("utf-8")
    return encoded_string

def get_image_description(api_key, uploaded_image):
    """
    Sends the uploaded image and API key to the Hyperbolic API and retrieves the response.
    """
    if not api_key:
        return {"error": "API key is required."}
    
    if uploaded_image is None:
        return {"error": "No image uploaded."}
    
    try:
        # Open the uploaded image
        img = Image.open(uploaded_image)
        base64_img = encode_image(img)
        
        api_endpoint = "https://api.hyperbolic.xyz/v1/chat/completions"
        
        headers = {
            "Content-Type": "application/json",
            "Authorization": f"Bearer {api_key}",
        }
        
        payload = {
            "messages": [
                {
                    "role": "user",
                    "content": [
                        {"type": "text", "text": "What is this image?"},
                        {
                            "type": "image_url",
                            "image_url": {"url": f"data:image/png;base64,{base64_img}"},
                        },
                    ],
                }
            ],
            "model": "Qwen/Qwen2-VL-72B-Instruct",
            "max_tokens": 2048,
            "temperature": 0.7,
            "top_p": 0.9,
        }
        
        response = requests.post(api_endpoint, headers=headers, json=payload)
        
        # Check if the request was successful
        if response.status_code == 200:
            return response.json()
        else:
            return {"error": f"API Error: {response.status_code} - {response.text}"}
    
    except Exception as e:
        return {"error": str(e)}

# Define the Gradio interface
with gr.Blocks() as demo:
    gr.Markdown(
        """
        # Image Description with Hyperbolic API

        Upload an image and enter your Hyperbolic API key to get a description of the image.
        """
    )
    
    with gr.Row():
        api_key_input = gr.Textbox(
            label="Hyperbolic API Key",
            type="password",
            placeholder="Enter your API key here",
            interactive=True
        )
    
    with gr.Row():
        image_input = gr.Image(
            label="Upload Image",
            type="filepath"
            # Removed the 'tool' parameter to ensure compatibility
        )
    
    with gr.Row():
        submit_button = gr.Button("Get Description")
    
    output = gr.JSON(label="API Response")
    
    # Define the button click event
    submit_button.click(
        fn=get_image_description,
        inputs=[api_key_input, image_input],
        outputs=output
    )
    
    gr.Markdown(
        """
        ---
        **Note:** Your API key is used only for this session and is not stored.
        """
    )

# Launch the Gradio app
if __name__ == "__main__":
    demo.launch()