app.py

import os
import gradio as gr
import requests
from groq import Groq

# Initialize Groq client
visionkey = os.getenv("GroqVision")
client = Groq(api_key=visionkey)

# Your imgbb API key
imagekey = os.getenv("ImageAPI")
IMGBB_API_KEY = imagekey

def upload_image_to_imgbb(image_path):
    """Uploads an image to imgbb and returns the URL."""
    url = f"https://api.imgbb.com/1/upload?key={IMGBB_API_KEY}"
    with open(image_path, "rb") as image_file:
        payload = {"image": image_file.read()}
        response = requests.post(url, files=payload)
        if response.status_code == 200:
            return response.json()["data"]["url"]
        else:
            raise ValueError(f"Image upload failed: {response.json()}")

def analyze_image(image, instruction):
    """Analyzes the image using Groq's Llama 3.2 based on the instruction provided."""
    try:
        # Save the uploaded image locally
        image_path = "uploaded_image.png"
        image.save(image_path)

        # Upload the image to imgbb
        image_url = upload_image_to_imgbb(image_path)

        # Call the Groq API to analyze the image
        completion = client.chat.completions.create(
            model="llama-3.2-90b-vision-preview",
            messages=[{
                "role": "user",
                "content": [
                    {"type": "text", "text": instruction},
                    {"type": "image_url", "image_url": {"url": image_url}}
                ]
            }],
            temperature=1,
            max_tokens=1024,
            top_p=1,
            stream=False,
            stop=None,
        )

        # Extract and return the response
        analysis = completion.choices[0].message.content  # Fix here to access content directly
        return analysis
    except Exception as e:
        return f"Error: {str(e)}"

# Gradio interface
iface = gr.Interface(
    fn=analyze_image,
    inputs=[
        gr.Image(type="pil", label="Upload Image"),
        gr.Textbox(label="Instruction", placeholder="Enter your analysis instruction here.", lines=2)
    ],
    outputs="text",
    title="Deep Image Analysis using LLM",
    description="Upload an image and provide instructions to analyze the image using Llama 3.2 90B Vision.",
    live=False,
)

# Launch the app
iface.launch()