import os
import gradio as gr
import requests
from transformers import pipeline

# Obtén el token desde las variables de entorno
hf_token = os.getenv("HF_TOKEN")

# Paso 1: Cargar el modelo de image-to-text
image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

# Paso 2: Función para llamar a la API de Qwen con el token seguro
def generate_recipe(description):
    url = "https://api-inference.huggingface.co/models/Qwen/Qwen2.5-72B-Instruct"
    headers = {"Authorization": f"Bearer {hf_token}"}
    
    # Añade el system input para definir el rol del modelo
    system_input = (
        "Act as a professional chef. Your task is to explain to a regular person "
        "how to cook a given dish, providing a step-by-step guide and a list of ingredients with exact quantities."
    )
    
    prompt = (
        f"{system_input} The dish is described as: {description}. "
        "Provide a list of ingredients followed by detailed cooking instructions."
    )
    
    payload = {
        "inputs": prompt,
        "parameters": {
            "max_new_tokens": 1500,
            "min_length": 500,
            "temperature": 0.7,
            "do_sample": True,
            "repetition_penalty": 1.2,
            "stop_sequences": ["\n\n"]
        }
    }

    response = requests.post(url, headers=headers, json=payload)
    response_data = response.json()
    
    if "error" in response_data:
        return "Error generating recipe: " + response_data["error"]
    
    return response_data[0]["generated_text"].replace(prompt, "").strip() if response_data else "No recipe generated."

# Paso 3: Define la función principal para procesar la imagen y generar la receta
def process_image(image):
    description = image_to_text(image)[0]['generated_text']
    recipe = generate_recipe(description)
    
    # Guardar la receta en un archivo temporal
    recipe_file_path = "/tmp/recipe.md"
    with open(recipe_file_path, "w") as file:
        file.write(recipe)
    
    return description, recipe, recipe_file_path

# Paso 4: Crear la interfaz de Gradio
iface = gr.Interface(
    fn=process_image,
    inputs=gr.Image(type="pil"),
    outputs=[
        gr.Textbox(label="Description"),
        gr.Text(label="Recipe"),
        gr.File(label="Download Recipe")  # Botón para descargar el archivo
    ],
    title="Recipe Generator from Dish Image",
    description="Upload an image of a dish to get a description, ingredient list, and step-by-step recipe."
)

# Lanzar la aplicación de Gradio
iface.launch()