import gradio as gr
import tensorflow
import numpy as np
import cv2 as cv
import requests
import time
import os

host = os.environ.get("host")
code = os.environ.get("code")
model = os.environ.get("model")
data = None
model = None
image = None
prediction = None
labels = None
max_label_index = None
max_prediction_value = -1

print('START')
np.set_printoptions(suppress=True)

model = tensorflow.keras.models.load_model('keras_model.h5')
data = np.ndarray(shape=(1, 224, 224, 3), dtype=np.float32)

with open("labels.txt", "r") as file:
    labels = file.read().splitlines()

def classify(image_path):
    try:
        image = cv.imread(image_path)
        image = cv.resize(image, (224, 224))
        image_array = np.asarray(image)
        normalized_image_array = (image_array.astype(np.float32) / 127.0) - 1
        data[0] = normalized_image_array
        prediction = model.predict(data)

        print('Prediction')

        for i, label in enumerate(labels):
            prediction_value = float(prediction[0][i])
            rounded_value = round(prediction_value, 2)
            print(f'{label}: {rounded_value}')

            if prediction_value > max_prediction_value:
                max_label_index = i
                max_prediction_value = prediction_value

        if max_label_index is not None:
            max_label = labels[max_label_index].split(' ', 1)[1]
            print(f'Maximum Prediction: {max_label} with a value of {round(max_prediction_value, 2)}')

            time.sleep(1)
            print("\nWays to dispose this waste: " + max_label)
            payload = [
                {"role": "system", "content": "You are a helpful assistant."},
                {"role": "user", "content": "Give me the steps to dispose this waste in bulleting points 5 max: " + "Plastic"}
            ]

            response = requests.post(host, json={
                "messages": payload,
                "model": model,
                "temperature": 0.5,
                "presence_penalty": 0,
                "frequency_penalty": 0,
                "top_p": 1
            }).json()

            return response["choices"][0]["message"]["content"]

    except Exception as e:
        return f"An error occurred: {e}"

iface = gr.Interface(
    fn=classify,
    inputs="text",
    outputs="text",
    title="Waste Classifier",
    description="Upload an image to classify and get disposal instructions."
)
iface.launch()