import os
import streamlit as st
import tensorflow as tf
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing.image import img_to_array, load_img
import numpy as np
import requests
from PIL import Image

# Set Groq API key in environment variable
os.environ['GROQ_API_KEY'] = "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"
GROQ_API_KEY = os.getenv('GROQ_API_KEY')

# Load pre-trained models (assumed to be in the same directory or provide the correct path)
classification_model = load_model('classification_model.h5')  # Model for normal/abnormal classification
organ_recognition_model = load_model('organ_recognition_model.h5')  # Model for organ recognition

def classify_image(image_path):
    """Classify the image as normal or abnormal."""
    image = load_img(image_path, target_size=(224, 224))
    image_array = img_to_array(image) / 255.0
    image_array = np.expand_dims(image_array, axis=0)
    prediction = classification_model.predict(image_array)
    return 'Abnormal' if prediction[0][0] > 0.5 else 'Normal'

def recognize_organ(image_path):
    """Recognize the organ in the image."""
    image = load_img(image_path, target_size=(224, 224))
    image_array = img_to_array(image) / 255.0
    image_array = np.expand_dims(image_array, axis=0)
    prediction = organ_recognition_model.predict(image_array)
    organ_classes = ['Lung', 'Heart', 'Brain']  # Example classes
    return organ_classes[np.argmax(prediction)]

def get_ai_insights(organ):
    """Fetch AI-based insights about the organ using Groq API."""
    url = "https://api.groq.com/v1/insights"
    headers = {"Authorization": f"Bearer {GROQ_API_KEY}", "Content-Type": "application/json"}
    data = {"query": f"Provide detailed insights about {organ} X-ray, its diseases, and treatments."}
    response = requests.post(url, headers=headers, json=data)
    if response.status_code == 200:
        return response.json().get("insights", "No insights available.")
    else:
        return "Failed to fetch insights. Please try again later."

def main():
    st.title("Medical Image Classification App")
    st.sidebar.title("Navigation")
    
    uploaded_file = st.file_uploader("Upload an X-ray or MRI image", type=["jpg", "jpeg", "png"])

    if uploaded_file:
        image = Image.open(uploaded_file)
        st.image(image, caption="Uploaded Image", use_column_width=True)
        
        with open("temp_image.jpg", "wb") as f:
            f.write(uploaded_file.getbuffer())

        st.write("### Classification Result")
        result = classify_image("temp_image.jpg")
        st.write(f"The X-ray is classified as: **{result}**")

        st.write("### Organ Recognition")
        organ = recognize_organ("temp_image.jpg")
        st.write(f"Recognized Organ: **{organ}**")

        st.write("### AI-Based Insights")
        insights = get_ai_insights(organ)
        st.write(insights)

if __name__ == "__main__":
    main()